INDEX

Explanations

names or entities containing the word "J" followed by another specific character or word

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals, particularly in a cultural or artistic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 predec

-0.74

ãĤª

-0.73

avorite

-0.71

uity

-0.64

 sarc

-0.61

 encount

-0.61

 srfAttach

-0.61

achev

-0.60

sufficient

-0.60

etheless

-0.60

POSITIVE LOGITS

neys

0.85

 Marriott

0.81

 Rowling

0.80

ansen

0.75

dan

0.75

usalem

0.73

 Ballard

0.72

ernaut

0.71

ney

0.68

 Lumpur

0.67

Activations Density 0.240%

names or entities containing the word "J" followed by another specific character or word

mentions of individuals, particularly in a cultural or artistic context

No Comments

No Known Activations