INDEX

Explanations

words related to famous individuals

oai_token-act-pair · gpt-3.5-turbo

repeated letters or sequences in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 debit

-0.68

 Scion

-0.56

 chains

-0.56

 elig

-0.55

hammad

-0.55

 illum

-0.55

 consolidation

-0.54

 durable

-0.53

 tops

-0.53

 sterling

-0.52

POSITIVE LOGITS

ilus

0.85

obic

0.73

urnal

0.72

selves

0.70

Henry

0.69

virt

0.68

ãĤ¼

0.68

ogenous

0.67

igen

0.65

throp

0.65

Activations Density 0.051%

words related to famous individuals

repeated letters or sequences in words

No Comments

No Known Activations