INDEX

Explanations

numeric values related to measurements or quantities

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics

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

nam

-0.88

fare

-0.87

hof

-0.85

ellen

-0.81

 Organisation

-0.80

algia

-0.79

estine

-0.78

sworth

-0.78

oha

-0.77

aways

-0.77

POSITIVE LOGITS

acebook

0.79

ault

0.78

PDATE

0.75

auld

0.71

vernment

0.71

MHz

0.70

 nerve

0.70

aution

0.69

pmwiki

0.68

 cylinders

0.67

Activations Density 0.044%

numeric values related to measurements or quantities

numerical data or statistics

No Comments

No Known Activations