INDEX

Explanations

the word "Whoever" at the beginning of sentences

oai_token-act-pair · gpt-3.5-turbo

the word "whoever" 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 @ 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

enthal

-0.95

eda

-0.84

ey

-0.74

aci

-0.74

IZ

-0.73

MSN

-0.73

end

-0.69

ARI

-0.68

ees

-0.68

 Roses

-0.67

POSITIVE LOGITS

soever

0.99

ftime

0.87

 else

0.84

 whoever

0.83

 Whoever

0.81

perty

0.78

obook

0.76

Whoever

0.75

wcsstore

0.70

 desired

0.68

Activations Density 0.010%

the word "Whoever" at the beginning of sentences

the word "whoever" in various contexts

No Comments

No Known Activations