INDEX

Explanations

dates and names in a specific format

oai_token-act-pair · gpt-3.5-turbo

delimiter tokens or placeholders in the text

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

 triv

-0.55

 compliant

-0.55

 disposable

-0.53

Sov

-0.52

'."

-0.49

 comprom

-0.48

 stale

-0.48

 disadvant

-0.46

 justifying

-0.46

 unbeliev

-0.46

POSITIVE LOGITS

itone

0.69

itars

0.57

çĶ°

0.53

ãĥĬ

0.50

cussion

0.50

ragon

0.49

ahu

0.48

 Seas

0.48

idas

0.48

selage

0.47

Activations Density 1.821%

dates and names in a specific format

delimiter tokens or placeholders in the text

No Comments

No Known Activations