INDEX

Explanations

locations or places outside buildings or establishments

oai_token-act-pair · gpt-3.5-turbo

references to locations or events occurring outside

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

Percent

-0.74

oleon

-0.72

oka

-0.72

XX

-0.71

olk

-0.69

Lay

-0.66

information

-0.63

uncle

-0.63

lda

-0.63

orah

-0.63

POSITIVE LOGITS

 patio

0.74

ModLoader

0.70

 Indies

0.68

perty

0.67

ntil

0.67

 Stamford

0.66

 undermin

0.64

eatures

0.63

 adolesc

0.63

 enclosure

0.62

Activations Density 0.021%

locations or places outside buildings or establishments

references to locations or events occurring outside

No Comments

No Known Activations