INDEX

Explanations

phrases related to specific professions or characteristics describing people

oai_token-act-pair · gpt-3.5-turbo

words that denote various social roles and identities

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

tails

-0.74

izens

-0.71

 regions

-0.70

Us

-0.70

rams

-0.69

 Lans

-0.68

ouls

-0.67

 slopes

-0.67

olas

-0.66

 bins

-0.66

POSITIVE LOGITS

digy

0.79

 unto

0.76

iste

0.75

ess

0.74

chuk

0.72

 herself

0.72

smith

0.71

alyst

0.70

 myself

0.70

nik

0.69

Activations Density 0.278%

phrases related to specific professions or characteristics describing people

words that denote various social roles and identities

No Comments

No Known Activations