INDEX

Explanations

photographs or references to photographs

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "photograph" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

inence

-0.69

woods

-0.68

road

-0.68

steen

-0.67

ught

-0.66

onge

-0.63

ful

-0.62

 disg

-0.62

sei

-0.62

ulhu

-0.61

POSITIVE LOGITS

ographs

1.14

 photographs

1.04

 photographed

1.04

 Photograph

1.02

photos

1.00

 photograph

0.99

 photographers

0.98

ographers

0.96

ynthesis

0.96

ograph

0.95

Activations Density 0.018%

photographs or references to photographs

occurrences of the word "photograph" and its variations

No Comments

No Known Activations