INDEX

Explanations

proper nouns related to different locations and person names

oai_token-act-pair · gpt-3.5-turbo

components related to locations or geographical names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ukong

-0.72

 encount

-0.69

geries

-0.64

 convol

-0.64

accompan

-0.61

orsche

-0.59

event

-0.59

healthy

-0.58

 reconc

-0.58

 ende

-0.58

POSITIVE LOGITS

Ì

0.79

Ì¶

0.78

Ã³

0.78

Ö¼

0.78

ÃĽ

0.73

uez

0.73

Ð²

0.72

Ã¡

0.72

Í

0.72

etus

0.72

Activations Density 0.165%

proper nouns related to different locations and person names

components related to locations or geographical names

No Comments

No Known Activations