INDEX

Explanations

terms related to communication or communal activities/themes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "commun" and its variations, indicating a focus on themes associated with communication and community

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BALL

-0.90

olkien

-0.85

OPLE

-0.75

IELD

-0.71

OHN

-0.69

 Lank

-0.69

DonaldTrump

-0.68

terday

-0.66

!/

-0.65

leaf

-0.64

POSITIVE LOGITS

icator

1.47

icators

1.32

icable

1.31

icating

1.30

icative

1.20

icate

1.13

icated

1.12

ications

1.11

ique

1.10

icates

1.10

Activations Density 0.017%

terms related to communication or communal activities/themes

instances of the word "commun" and its variations, indicating a focus on themes associated with communication and community

No Comments

No Known Activations