INDEX

Explanations

items that have been specifically marked or identified with a label

oai_token-act-pair · gpt-3.5-turbo

terms related to labeling or categorizing objects or ideas

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

ramid

-0.75

=-=-

-0.73

ppa

-0.72

yre

-0.72

perty

-0.70

vati

-0.69

abama

-0.68

hire

-0.67

 compr

-0.67

vous

-0.67

POSITIVE LOGITS

phas

0.85

ging

0.69

 unfit

0.68

ged

0.67

own

0.67

 labelled

0.67

 labeled

0.66

 labeling

0.64

 loyalty

0.64

 branded

0.63

Activations Density 0.034%

items that have been specifically marked or identified with a label

terms related to labeling or categorizing objects or ideas

No Comments

No Known Activations