INDEX

Explanations

the verb "blame" followed by a target for attribution

oai_token-act-pair · gpt-3.5-turbo

key phrases and statements indicating strong opinions or significant events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orsi

-0.70

 demonstrating

-0.64

 thanking

-0.64

 referring

-0.63

 Citation

-0.63

 telling

-0.63

 (Â£

-0.61

/$

-0.60

 reprint

-0.60

 disclosing

-0.60

POSITIVE LOGITS

endas

0.74

ictionary

0.73

thood

0.71

border

0.70

iped

0.70

DIT

0.68

aughs

0.67

ãĥīãĥ©

0.65

hetics

0.64

aband

0.64

Activations Density 1.656%

the verb "blame" followed by a target for attribution

key phrases and statements indicating strong opinions or significant events

No Comments

No Known Activations