INDEX

Explanations

words related to historical periods, famous movies, and filmmakers

oai_token-act-pair · gpt-3.5-turbo

references to specific films and their associated themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

redo

-0.78

leader

-0.77

rooms

-0.75

hips

-0.73

sheet

-0.73

lying

-0.69

sheets

-0.69

isSpecialOrderable

-0.68

held

-0.68

rated

-0.68

POSITIVE LOGITS

osaurs

1.22

 Jurassic

1.15

assic

0.97

 Park

0.88

osaurus

0.87

aceous

0.81

itect

0.72

 Dinosaur

0.71

olit

0.70

ãĥ©ãĥ³

0.69

Activations Density 0.010%

words related to historical periods, famous movies, and filmmakers

references to specific films and their associated themes

No Comments

No Known Activations