INDEX

Explanations

pronouns referring to unspecified individuals

oai_token-act-pair · gpt-3.5-turbo

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

 Schn

-0.55

 Paradise

-0.55

 Cinema

-0.51

 remake

-0.51

Md

-0.51

 Celebrity

-0.51

 applause

-0.50

 Tablet

-0.50

 accommod

-0.50

 Privacy

-0.50

POSITIVE LOGITS

ild

1.02

ional

0.98

ement

0.97

eline

0.95

athy

0.95

adic

0.93

inas

0.89

alos

0.89

ores

0.89

eless

0.88

Activations Density 1.282%

pronouns referring to unspecified individuals

No Comments

No Known Activations