INDEX

Explanations

mentions of the word "Cere" or words related to it

oai_token-act-pair · gpt-3.5-turbo

terms related to cerebellar conditions and related medical topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lihood

-0.80

 paradise

-0.66

eties

-0.62

Http

-0.61

laws

-0.61

ARP

-0.60

 goodwill

-0.59

 mitigation

-0.58

/**

-0.58

!/

-0.58

POSITIVE LOGITS

flies

0.93

mony

0.89

pillar

0.86

bral

0.83

ific

0.83

ificial

0.83

bell

0.80

utical

0.76

pill

0.75

rupted

0.74

Activations Density 0.091%

mentions of the word "Cere" or words related to it

terms related to cerebellar conditions and related medical topics

No Comments

No Known Activations