INDEX

Explanations

mentions of specific landmarks or locations, particularly Piers

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or names, particularly related to "Pier."

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

 Bihar

-0.72

 Unch

-0.70

Clo

-0.68

arily

-0.66

aries

-0.66

avez

-0.64

eem

-0.63

akes

-0.63

ESE

-0.62

esley

-0.62

POSITIVE LOGITS

 Pier

0.95

cer

0.94

asus

0.90

rette

0.90

 pier

0.90

idon

0.88

reon

0.86

cers

0.85

nown

0.84

achy

0.83

Activations Density 0.017%

mentions of specific landmarks or locations, particularly Piers

references to specific locations or names, particularly related to "Pier."

No Comments

No Known Activations