INDEX

Explanations

words related to choices or options

oai_token-act-pair · gpt-3.5-turbo

the word "or" used in various contexts

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

 horizont

-0.72

onday

-0.67

elong

-0.65

Dear

-0.63

ilton

-0.61

achine

-0.60

idem

-0.60

opian

-0.59

pter

-0.59

agra

-0.59

POSITIVE LOGITS

acles

1.30

acle

1.27

chard

1.27

Else

1.26

lando

1.13

chid

1.11

acular

1.08

ifice

1.05

nam

1.05

ific

1.02

Activations Density 0.107%

words related to choices or options

the word "or" used in various contexts

No Comments

No Known Activations