INDEX

Explanations

phrases indicating collective decision-making or team action

oai_token-act-pair · gpt-3.5-turbo

references to collective experiences and teamwork

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

uates

-0.65

atory

-0.65

 Eleven

-0.61

ftime

-0.59

 Rash

-0.59

 totality

-0.59

more

-0.58

CENT

-0.58

rx

-0.57

alky

-0.56

POSITIVE LOGITS

've

1.28

'll

1.20

're

1.18

'd

1.10

athered

1.00

selves

0.96

ighed

0.96

asel

0.91

eding

0.90

 encount

0.89

Activations Density 0.256%

phrases indicating collective decision-making or team action

references to collective experiences and teamwork

No Comments

No Known Activations