INDEX

Explanations

proper nouns related to various locations and organizations

oai_token-act-pair · gpt-3.5-turbo

geographical names and locations

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

Americ

-0.65

omsky

-0.64

aci

-0.64

aer

-0.61

ente

-0.60

estyles

-0.60

adobe

-0.59

uers

-0.59

geoning

-0.59

sych

-0.59

POSITIVE LOGITS

 outper

0.72

 counterpart

0.72

 Stadium

0.71

's

0.68

 lacks

0.64

 itself

0.62

 fans

0.62

 substitution

0.60

 monop

0.60

ians

0.59

Activations Density 0.383%

proper nouns related to various locations and organizations

geographical names and locations

No Comments

No Known Activations