INDEX

Explanations

locations or places mentioned in text

oai_token-act-pair · gpt-3.5-turbo

locations, dates, and events

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

thood

-0.77

natureconservancy

-0.69

reated

-0.67

ror

-0.67

inyl

-0.66

iral

-0.66

onym

-0.65

selves

-0.60

rez

-0.60

rect

-0.60

POSITIVE LOGITS

 Calif

1.12

 Colo

1.00

Fla

0.98

TX

0.88

Ala

0.86

 Illinois

0.85

 Tenn

0.83

 Tennessee

0.82

TN

0.82

 Missouri

0.81

Activations Density 0.155%

locations or places mentioned in text

locations, dates, and events

No Comments

No Known Activations