INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

instances of specific letters or combinations of letters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 flares

-0.74

 flare

-0.68

pse

-0.64

 Rosenberg

-0.61

 Stub

-0.61

Osw

-0.61

arlane

-0.59

DEP

-0.59

 challeng

-0.59

 contrace

-0.58

POSITIVE LOGITS

ï¸ı

0.91

oise

0.78

edu

0.75

Ã©

0.73

hai

0.71

merce

0.71

oir

0.70

 Rouge

0.68

schild

0.67

ailable

0.67

Activations Density 0.129%

proper nouns or names

instances of specific letters or combinations of letters

No Comments

No Known Activations