INDEX

Explanations

specific mentions of an entity called "Friends" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Friends" in various contexts, indicating a focus on friendship or community connections

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

 bearer

-0.68

 concussion

-0.65

OTT

-0.63

otal

-0.62

arcity

-0.60

artifacts

-0.59

OUT

-0.59

 utilitarian

-0.59

ameron

-0.59

stall

-0.59

POSITIVE LOGITS

hips

1.19

 Friends

1.07

liest

0.98

liness

0.92

Friends

0.88

busters

0.87

ships

0.84

ilial

0.81

lier

0.81

 Friend

0.80

Activations Density 0.023%

specific mentions of an entity called "Friends" in various contexts

mentions of the word "Friends" in various contexts, indicating a focus on friendship or community connections

No Comments

No Known Activations