INDEX

Explanations

words related to actions or characteristics that are alarming or threatening

oai_token-act-pair · gpt-3.5-turbo

gerund forms of verbs indicating actions or processes

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

ipedia

-0.78

imeo

-0.77

talk

-0.73

fg

-0.70

IFIED

-0.69

ONEY

-0.69

trak

-0.69

authent

-0.67

elo

-0.66

cci

-0.66

POSITIVE LOGITS

tons

1.00

 extraord

0.94

aukee

0.85

 adventures

0.78

 spree

0.77

 exped

0.76

 tendencies

0.76

quished

0.75

 stunts

0.74

 subsequ

0.72

Activations Density 0.088%

words related to actions or characteristics that are alarming or threatening

gerund forms of verbs indicating actions or processes

No Comments

No Known Activations