INDEX

Explanations

phrases indicating a requirement, prohibition, or consideration of opinions or actions

oai_token-act-pair · gpt-3.5-turbo

the word "don’t"

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

cised

-0.65

 Completed

-0.64

 afore

-0.63

 Casting

-0.63

 Dise

-0.62

ipel

-0.61

 Learning

-0.61

milo

-0.60

 vanquished

-0.58

 Semi

-0.57

POSITIVE LOGITS

't

1.43

ned

1.13

ates

0.92

ning

0.91

atives

0.90

nell

0.85

nels

0.84

etsk

0.83

uts

0.82

kie

0.81

Activations Density 0.112%

phrases indicating a requirement, prohibition, or consideration of opinions or actions

the word "don’t"

No Comments

No Known Activations