INDEX

Explanations

phrases related to personal qualities and characteristics

oai_token-act-pair · gpt-3.5-turbo

statements related to emotional or psychological observations

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

swick

-0.88

asio

-0.70

ESE

-0.69

wright

-0.69

afety

-0.69

hers

-0.66

SHIP

-0.64

stanbul

-0.64

bia

-0.62

thora

-0.62

POSITIVE LOGITS

 albeit

0.92

gradient

0.85

etc

0.76

 encomp

0.72

 economical

0.71

huh

0.69

sounding

0.69

minded

0.68

itar

0.64

 contro

0.64

Activations Density 0.289%

phrases related to personal qualities and characteristics

statements related to emotional or psychological observations

No Comments

No Known Activations