INDEX

Explanations

phrases indicating negation or denial

oai_token-act-pair · gpt-3.5-turbo

the phrase "by no means."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Metatron

-0.63

 Presence

-0.63

 Carbuncle

-0.58

lycer

-0.56

igree

-0.55

 Strateg

-0.54

 Paint

-0.54

dor

-0.54

iership

-0.53

 Dial

-0.53

POSITIVE LOGITS

xious

0.99

onday

0.97

xus

0.94

ones

0.88

except

0.87

oses

0.87

 avail

0.83

 longer

0.83

otrop

0.83

 particular

0.76

Activations Density 0.054%

phrases indicating negation or denial

the phrase "by no means."

No Comments

No Known Activations