INDEX

Explanations

dates specified in the format Day, Month, Year

oai_token-act-pair · gpt-3.5-turbo

specific dates or numerical values relevant to events

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

tumblr

-0.71

pron

-0.69

akespe

-0.68

anke

-0.67

ãĥį

-0.66

orable

-0.65

pered

-0.64

essors

-0.64

dinand

-0.63

orc

-0.63

POSITIVE LOGITS

externalActionCode

0.76

th

0.76

 Kass

0.72

 sidx

0.68

rd

0.68

omore

0.66

 onwards

0.65

ths

0.64

 ambush

0.63

 mornings

0.62

Activations Density 0.069%

dates specified in the format Day, Month, Year

specific dates or numerical values relevant to events

No Comments

No Known Activations