INDEX

Explanations

numbers or numerical values

oai_token-act-pair · gpt-3.5-turbo

numerical values or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ItemImage

-0.66

 conduc

-0.61

Ü

-0.61

creen

-0.56

ability

-0.56

ercise

-0.56

cerning

-0.56

 Spears

-0.55

 cold

-0.55

 indo

-0.54

POSITIVE LOGITS

xff

1.26

xc

1.01

xa

0.96

xd

0.96

xe

0.96

xb

0.91

0.90

0.87

0.82

uer

0.80

Activations Density 0.042%

numbers or numerical values

numerical values or statistics

No Comments

No Known Activations