INDEX

Explanations

the word "feel" followed by a verb

oai_token-act-pair · gpt-3.5-turbo

expressions of personal feelings and emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Camer

-0.69

esan

-0.68

 Extras

-0.66

 Display

-0.65

adish

-0.65

angle

-0.65

 Tactics

-0.64

 Correspond

-0.63

swick

-0.62

 Agricultural

-0.62

POSITIVE LOGITS

 comfortable

1.06

 compelled

1.04

 uneasy

0.99

 strongly

0.94

 obligated

0.89

 ashamed

0.89

 confident

0.89

 passionately

0.88

 uncomfortable

0.87

rils

0.87

Activations Density 0.040%

the word "feel" followed by a verb

expressions of personal feelings and emotions

No Comments

No Known Activations