INDEX

Explanations

words or word fragments related to the name "Laura"

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals and places

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

eering

-0.65

eer

-0.61

INC

-0.60

PC

-0.59

FU

-0.59

 Nile

-0.58

 backdrop

-0.58

 Reloaded

-0.57

pocket

-0.57

ECO

-0.57

POSITIVE LOGITS

issan

1.14

asia

0.93

icular

0.89

thur

0.87

ice

0.87

ouse

0.86

idon

0.85

asma

0.85

rible

0.84

acles

0.83

Activations Density 0.047%

words or word fragments related to the name "Laura"

proper nouns, particularly names of individuals and places

No Comments

No Known Activations