INDEX

Explanations

numbers combined with specific keywords related to details such as financial values, dimensions, and limits

oai_token-act-pair · gpt-3.5-turbo

numerical values, especially related to measurement or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

veyard

-0.83

creen

-0.81

vet

-0.79

vern

-0.75

akening

-0.67

 attendant

-0.67

imei

-0.66

ppa

-0.62

hunt

-0.61

 shape

-0.61

POSITIVE LOGITS

%-

0.86

nm

0.80

0.79

0.78

 Thieves

0.74

%.

0.70

 acres

0.70

 percent

0.69

dfx

0.68

Activations Density 0.049%

numbers combined with specific keywords related to details such as financial values, dimensions, and limits

numerical values, especially related to measurement or specifications

No Comments

No Known Activations