INDEX

Explanations

words related to tough or challenging situations

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to different types of slums and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 concess

-0.75

 Surviv

-0.65

ICAN

-0.64

 disg

-0.62

åº

-0.59

 Tanz

-0.59

 Fallen

-0.58

 astron

-0.58

ITNESS

-0.57

OTOS

-0.57

POSITIVE LOGITS

odan

0.89

ppe

0.81

ï¸ı

0.79

tarians

0.76

inki

0.75

pees

0.74

ando

0.73

deals

0.73

puff

0.72

iping

0.72

Activations Density 0.074%

words related to tough or challenging situations

words and phrases related to different types of slums and their characteristics

No Comments

No Known Activations