INDEX

Explanations

statements that confirm suspicions or established facts

oai_token-act-pair · gpt-3.5-turbo

references to data supporting common beliefs or suspicions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 disposal

-0.84

selection

-0.73

 Doodle

-0.72

 diversion

-0.68

 selection

-0.67

 compares

-0.67

itiz

-0.66

 Volunteers

-0.65

gins

-0.65

 PHOTO

-0.63

POSITIVE LOGITS

 anecd

0.91

 debunked

0.91

 already

0.90

 loudly

0.88

 previously

0.85

 repeatedly

0.85

false

0.83

 painfully

0.83

 plainly

0.81

 theorem

0.80

Activations Density 0.206%

statements that confirm suspicions or established facts

references to data supporting common beliefs or suspicions

No Comments

No Known Activations