INDEX

Explanations

names of people and locations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "and"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

onica

-0.69

Tes

-0.67

,)

-0.64

busters

-0.64

 Powered

-0.63

enger

-0.63

Times

-0.62

SE

-0.62

png

-0.62

POSITIVE LOGITS

 consequently

1.05

 secondly

1.04

 thence

0.98

 furthermore

0.97

 hence

0.96

 therefore

0.93

 thus

0.89

 moreover

0.89

 thereby

0.89

 then

0.82

Activations Density 0.228%

names of people and locations

instances of the word "and"

No Comments

No Known Activations