INDEX

Explanations

words related to images or visual content

oai_token-act-pair · gpt-3.5-turbo

references to images or pictures

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

iant

-0.76

vernment

-0.75

rador

-0.72

edient

-0.72

aughs

-0.72

iance

-0.70

bard

-0.69

ible

-0.69

orne

-0.69

hement

-0.68

POSITIVE LOGITS

picture

0.87

 depicting

0.84

 galleries

0.84

Pic

0.83

Pic

0.82

Pict

0.81

que

0.80

img

0.78

 mosa

0.78

>>>>>>>>

0.78

Activations Density 0.023%

words related to images or visual content

references to images or pictures

No Comments

No Known Activations