INDEX

Explanations

locations or events related to captioned images

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Hide" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

etheless

-0.98

odic

-0.81

bably

-0.79

ammy

-0.76

ionic

-0.76

eele

-0.74

ilingual

-0.72

ulz

-0.68

theless

-0.68

arbon

-0.68

POSITIVE LOGITS

 Caption

1.14

 Hide

1.00

Hide

0.93

away

0.90

ously

0.82

Streamer

0.77

chell

0.71

hide

0.71

DEN

0.69

 Flavoring

0.68

Activations Density 0.007%

locations or events related to captioned images

instances of the word "Hide" and its variations

No Comments

No Known Activations