INDEX

Explanations

pronouns referring to individuals

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the presence and actions of specific subjects or entities

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

Skip

-0.69

Minor

-0.69

Times

-0.65

Gw

-0.64

OWER

-0.62

Ĥ¬

-0.62

 Offense

-0.62

Sexual

-0.62

YP

-0.61

imum

-0.61

POSITIVE LOGITS

'll

1.08

 consequently

1.06

 accordingly

0.94

're

0.91

 certainly

0.91

've

0.88

 therefore

0.83

 thereafter

0.82

 shouldn

0.81

 afterward

0.79

Activations Density 0.292%

pronouns referring to individuals

phrases indicating the presence and actions of specific subjects or entities

No Comments

No Known Activations