INDEX

Explanations

phrases indicating significance or importance

oai_token-act-pair · gpt-3.5-turbo

frequent phrases that indicate emphasis, specificity, or attributes in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

mare

-0.76

 antioxid

-0.73

interstitial

-0.72

arta

-0.71

mares

-0.71

 VIDEOS

-0.70

bara

-0.69

awa

-0.69

ethy

-0.65

Dialogue

-0.62

POSITIVE LOGITS

 originally

1.07

 instrumental

0.98

 initially

0.91

 last

0.84

 unsuccessful

0.84

 conceived

0.78

 successful

0.77

 earlier

0.77

 previously

0.75

 gracious

0.74

Activations Density 0.544%

phrases indicating significance or importance

frequent phrases that indicate emphasis, specificity, or attributes in descriptions

No Comments

No Known Activations