INDEX

Explanations

photo-related terms

oai_token-act-pair · gpt-3.5-turbo

references to photographs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ensable

-0.88

ricular

-0.80

phasis

-0.74

inence

-0.72

ressive

-0.72

ulhu

-0.72

cair

-0.72

merce

-0.72

hurst

-0.68

avanaugh

-0.68

POSITIVE LOGITS

journal

1.17

ynthesis

1.11

>>>>>>>>

0.97

photos

0.96

electric

0.91

 shoots

0.90

 illustration

0.90

 shoot

0.89

ops

0.85

ynt

0.85

Activations Density 0.036%

photo-related terms

references to photographs

No Comments

No Known Activations