INDEX

Explanations

references to maps

oai_token-act-pair · gpt-3.5-turbo

references to maps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

nuts

-0.85

icer

-0.85

ruciating

-0.78

aneous

-0.76

nder

-0.75

ntil

-0.74

weeney

-0.74

quished

-0.72

ente

-0.71

usters

-0.71

POSITIVE LOGITS

ographer

0.83

map

0.83

map

0.77

 maps

0.73

makers

0.70

Map

0.70

maker

0.70

 tiles

0.70

hack

0.70

ãĤº

0.70

Activations Density 0.012%

references to maps

references to maps

No Comments

No Known Activations