INDEX

Explanations

differences in various contexts or characteristics

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of individual differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ãĥİ

-0.81

rollers

-0.79

ATA

-0.76

roller

-0.73

ODE

-0.73

×Ķ

-0.72

ergy

-0.72

DA

-0.71

GE

-0.69

ãĥ«

-0.68

POSITIVE LOGITS

yip

0.94

 between

0.90

between

0.87

ials

0.82

iveness

0.82

ially

0.81

iating

0.80

 differe

0.78

 warr

0.76

 citiz

0.74

Activations Density 0.028%

differences in various contexts or characteristics

repeated mentions of individual differences

No Comments

No Known Activations