INDEX

Explanations

specific titles of books

oai_token-act-pair · gpt-3.5-turbo

references to books and authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 encount

-0.65

 projectile

-0.63

rouse

-0.62

 whisk

-0.60

 shenan

-0.59

PET

-0.59

 skelet

-0.58

 enforce

-0.58

 combo

-0.57

 quir

-0.57

POSITIVE LOGITS

 Versus

1.18

 Matters

1.15

 Without

1.15

 Lessons

1.15

 Secrets

1.11

 Manifest

1.09

 Revis

1.09

 Handbook

1.09

 Lies

1.08

 Lives

1.07

Activations Density 0.284%

specific titles of books

references to books and authors

No Comments

No Known Activations