INDEX

Explanations

propper nouns

oai_token-act-pair · gpt-3.5-turbo

the repeated occurrence of the substring "ne" within words

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

rador

-0.96

hips

-0.83

rament

-0.80

inarily

-0.79

allery

-0.77

 glim

-0.76

orsi

-0.76

rican

-0.74

enhagen

-0.74

ENCY

-0.73

POSITIVE LOGITS

arest

0.97

cht

0.96

jad

0.94

phrine

0.90

verend

0.90

zel

0.89

gan

0.89

cks

0.88

gger

0.86

zi

0.86

Activations Density 0.022%

propper nouns

the repeated occurrence of the substring "ne" within words

No Comments

No Known Activations