INDEX

Explanations

words related to behavioral actions or misconduct

oai_token-act-pair · gpt-3.5-turbo

references to behavior and behavioral studies or analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

IFIED

-0.79

istically

-0.78

itarian

-0.75

 Prometheus

-0.68

istries

-0.67

ITIES

-0.67

 Opera

-0.67

IAL

-0.65

 TEAM

-0.65

 Nadu

-0.65

POSITIVE LOGITS

aviour

1.43

aving

1.12

aved

1.02

avior

1.00

assing

0.97

avin

0.91

avement

0.90

av

0.87

akable

0.86

¡

0.85

Activations Density 0.030%

words related to behavioral actions or misconduct

references to behavior and behavioral studies or analysis

No Comments

No Known Activations