INDEX

Explanations

photographs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

steen

-0.74

woods

-0.73

onge

-0.68

inence

-0.67

road

-0.67

sei

-0.64

ricular

-0.62

lling

-0.62

govern

-0.62

ught

-0.62

POSITIVE LOGITS

ographs

1.08

 photographs

1.03

 photographed

1.03

 Photograph

1.00

photos

0.99

 photograph

0.96

 Phot

0.96

Phot

0.94

 photographers

0.93

 Photographer

0.93

Activations Density 0.021%

photographs

references to photographs

No Comments

No Known Activations