INDEX

Explanations

options or choices in a list

oai_token-act-pair · gpt-3.5-turbo

the word "or" 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

ocracy

-0.84

ocratic

-0.71

 Pony

-0.68

Material

-0.66

ocrat

-0.64

vertising

-0.64

ENE

-0.62

Words

-0.61

ocrats

-0.61

ETS

-0.59

POSITIVE LOGITS

chard

1.32

acle

1.28

 alternatively

1.26

chid

1.26

acles

1.19

Else

1.11

ifice

1.09

nam

1.09

acular

1.06

 otherwise

1.02

Activations Density 0.168%

options or choices in a list

the word "or" in various contexts

No Comments

No Known Activations