INDEX

Explanations

proper nouns or capitalized words

oai_token-act-pair · gpt-3.5-turbo

characters or symbols that denote the end of text

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

enegger

-0.91

anwhile

-0.82

 destro

-0.73

 referen

-0.68

mble

-0.67

ä»£

-0.66

 eleph

-0.65

raints

-0.63

chnology

-0.63

ierrez

-0.63

POSITIVE LOGITS

Coin

0.67

Fest

0.62

Py

0.62

 Street

0.62

Wiki

0.61

coin

0.61

Forge

0.60

han

0.59

Star

0.58

FP

0.58

Activations Density 0.546%

proper nouns or capitalized words

characters or symbols that denote the end of text

No Comments

No Known Activations