INDEX

Explanations

mentions of specific items or concepts like names or terms indicated by "of"

oai_token-act-pair · gpt-3.5-turbo

instances of blank or empty sections in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

respective

-0.61

 commute

-0.59

 submar

-0.59

 misunder

-0.58

 respons

-0.58

iste

-0.57

 campaigned

-0.57

accompan

-0.56

 reperto

-0.56

 visitor

-0.56

POSITIVE LOGITS

 course

0.98

course

0.95

 Course

0.92

icial

0.84

 Contents

0.84

 sorts

0.76

 Interest

0.74

 Devices

0.72

aughs

0.71

 Horror

0.71

Activations Density 0.051%

mentions of specific items or concepts like names or terms indicated by "of"

instances of blank or empty sections in the text

No Comments

No Known Activations