INDEX

Explanations

terms related to atomic energy and nuclear weapons

oai_token-act-pair · gpt-3.5-turbo

terms related to atomic and nuclear concepts

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

PE

-0.85

atche

-0.85

come

-0.85

CV

-0.79

WHERE

-0.76

regon

-0.76

comes

-0.76

shire

-0.75

Cro

-0.75

rd

-0.74

POSITIVE LOGITS

 atomic

1.13

 nucle

1.07

 atom

0.99

 bomb

0.95

 nucleus

0.94

atomic

0.93

 atoms

0.92

 iodine

0.90

 bombs

0.89

 physicist

0.87

Activations Density 0.007%

terms related to atomic energy and nuclear weapons

terms related to atomic and nuclear concepts

No Comments

No Known Activations