INDEX

Explanations

comparisons or rankings

oai_token-act-pair · gpt-3.5-turbo

terms related to frequency and popularity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

CHAT

-0.84

ĸļ

-0.78

ogenesis

-0.64

 Bunny

-0.64

Dialogue

-0.63

 Alone

-0.63

onto

-0.61

 Shirley

-0.59

 Bahamas

-0.59

 barr

-0.58

POSITIVE LOGITS

 imaginable

0.90

icipated

0.78

doms

0.74

ensical

0.72

ashtra

0.70

attering

0.69

ilers

0.68

hots

0.67

 includ

0.67

 âĶľ

0.66

Activations Density 1.054%

comparisons or rankings

terms related to frequency and popularity

No Comments

No Known Activations