INDEX

Explanations

phrases indicating a preference for one option over another

oai_token-act-pair · gpt-3.5-turbo

phrases that reflect a preference for one option or criterion over another

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

aeus

-0.76

aspers

-0.70

rend

-0.70

obal

-0.69

worm

-0.68

omach

-0.68

rake

-0.65

ospons

-0.64

cia

-0.63

hiba

-0.63

POSITIVE LOGITS

ãĤ¦ãĤ¹

0.71

 âĢİ

0.70

 theirs

0.69

 à¨

0.69

à¨

0.61

rather

0.60

GROUND

0.60

 Eternity

0.59

 others

0.59

iman

0.59

Activations Density 0.392%

phrases indicating a preference for one option over another

phrases that reflect a preference for one option or criterion over another

No Comments

No Known Activations