INDEX

Explanations

text enclosed within double asterisks, potentially indicating emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

special formatting or emphasis markers, such as asterisks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

liest

-0.77

liness

-0.70

ãĥ¼ãĥ«

-0.68

ly

-0.65

ugu

-0.65

 scattering

-0.64

eways

-0.63

leness

-0.63

vation

-0.63

ciating

-0.62

POSITIVE LOGITS

kw

0.89

Madison

0.85

taboola

0.83

///

0.80

DOWN

0.74

hole

0.74

/**

0.72

Ping

0.71

âĶģ

0.69

KER

0.69

Activations Density 0.014%

text enclosed within double asterisks, potentially indicating emphasis or importance

special formatting or emphasis markers, such as asterisks

No Comments

No Known Activations