INDEX

Explanations

phrases related to familiarity or personal connections

oai_token-act-pair · gpt-3.5-turbo

instances of the word "know" 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 @ 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

 voucher

-0.74

pex

-0.74

evin

-0.72

issions

-0.71

isco

-0.70

phrine

-0.70

 privatization

-0.67

 Antar

-0.67

itter

-0.67

inance

-0.66

POSITIVE LOGITS

lege

1.09

ledged

1.00

ledge

0.97

abouts

0.78

edge

0.78

 ABOUT

0.75

 beforehand

0.75

LED

0.74

how

0.74

nothing

0.73

Activations Density 0.054%

phrases related to familiarity or personal connections

instances of the word "know" and its variations

No Comments

No Known Activations