INDEX

Explanations

locations or areas within a city, particularly focusing on downtown areas

oai_token-act-pair · gpt-3.5-turbo

references to downtown areas

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ktop

-0.89

uid

-0.85

nir

-0.79

nikov

-0.77

alys

-0.77

aye

-0.76

uth

-0.75

laughter

-0.75

nell

-0.71

ula

-0.71

POSITIVE LOGITS

 Oakland

1.01

 Denver

0.99

 Manhattan

0.98

 Seattle

0.96

 Honolulu

0.96

 Toronto

0.95

 Raleigh

0.94

 Vancouver

0.94

Los

0.93

 Winnipeg

0.92

Activations Density 0.027%

locations or areas within a city, particularly focusing on downtown areas

references to downtown areas

No Comments

No Known Activations