INDEX

Explanations

mentions of the word "saw" or related phrases

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "saw" in various contexts

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

 foss

-0.78

itÃ©

-0.77

ysis

-0.73

istically

-0.70

istics

-0.70

oses

-0.69

 handshake

-0.67

 dosage

-0.63

 contraceptive

-0.62

 undis

-0.62

POSITIVE LOGITS

amura

1.08

nesday

1.02

yers

1.00

aii

0.99

atari

0.89

atche

0.88

mill

0.88

atoon

0.85

Saw

0.84

esome

0.82

Activations Density 0.014%

mentions of the word "saw" or related phrases

mentions of the word "saw" in various contexts

No Comments

No Known Activations