INDEX

Explanations

words related to geographic locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "land" in various contexts

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

 cumbers

-0.82

displayText

-0.73

ongyang

-0.73

 millenn

-0.69

 undermin

-0.67

unction

-0.67

berus

-0.66

 retribution

-0.65

hift

-0.63

FIN

-0.62

POSITIVE LOGITS

scape

1.08

marks

0.91

 Hills

0.88

 Park

0.85

 County

0.82

 Islands

0.82

estine

0.81

mont

0.80

ishly

0.78

ward

0.77

Activations Density 0.034%

words related to geographic locations

occurrences of the word "land" in various contexts

No Comments

No Known Activations