INDEX

Explanations

names or phrases with abbreviations and special characters embedded in them

oai_token-act-pair · gpt-3.5-turbo

words associated with specific names or proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 prol

-0.82

 puzz

-0.70

 pent

-0.70

 envy

-0.69

 hairs

-0.68

 hell

-0.68

 mainline

-0.67

 homebrew

-0.66

 starters

-0.65

 peac

-0.62

POSITIVE LOGITS

ady

0.98

atar

0.94

Ã¥

0.92

esh

0.92

irk

0.91

ade

0.91

ijn

0.91

offer

0.90

ond

0.90

itsu

0.89

Activations Density 0.218%

names or phrases with abbreviations and special characters embedded in them

words associated with specific names or proper nouns

No Comments

No Known Activations