INDEX

Explanations

mentions of or related to Google Maps

oai_token-act-pair · gpt-3.5-turbo

references to Google Maps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

nder

-0.89

nen

-0.84

inion

-0.78

gio

-0.77

osi

-0.77

rone

-0.77

isher

-0.73

cgi

-0.71

yards

-0.71

Thumbnail

-0.70

POSITIVE LOGITS

 Maps

0.90

 maps

0.85

ynthesis

0.81

 mapping

0.79

 mapped

0.78

ynt

0.77

Maps

0.73

obook

0.71

uggest

0.70

map

0.66

Activations Density 0.009%

mentions of or related to Google Maps

references to Google Maps

No Comments

No Known Activations