INDEX

Explanations

words related to negation or exclusion

oai_token-act-pair · gpt-3.5-turbo

negations related to social or legal situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

HAEL

-0.71

 Delivery

-0.65

manship

-0.62

 Presence

-0.61

 Puzz

-0.60

soType

-0.60

issance

-0.57

 Moves

-0.57

assetsadobe

-0.57

 Garr

-0.57

POSITIVE LOGITS

 necessarily

1.23

 ordinarily

1.15

 otherwise

1.10

 normally

1.04

 traditionally

1.00

 explicitly

0.91

 expressly

0.90

 previously

0.88

 overtly

0.87

 belong

0.83

Activations Density 0.190%

words related to negation or exclusion

negations related to social or legal situations

No Comments

No Known Activations