INDEX

Explanations

keywords related to atoms and atomic interactions

oai_token-act-pair · gpt-3.5-turbo

references to atoms and their properties

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

 Fargo

-0.82

PE

-0.79

Guard

-0.75

VICE

-0.72

dk

-0.71

Executive

-0.70

Score

-0.69

Cro

-0.68

ORD

-0.68

HCR

-0.67

POSITIVE LOGITS

 atoms

1.09

 atom

1.05

aceous

0.99

ctrl

0.91

 Atom

0.86

 physicist

0.84

atom

0.82

 latt

0.82

ility

0.81

azes

0.81

Activations Density 0.008%

keywords related to atoms and atomic interactions

references to atoms and their properties

No Comments

No Known Activations