INDEX

Explanations

numeric expressions in the format of time, such as hours and minutes

oai_token-act-pair · gpt-3.5-turbo

references to numbered locations or time codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

inates

-0.80

 tradem

-0.70

inate

-0.69

abwe

-0.67

icably

-0.65

ulously

-0.62

kens

-0.62

pmwiki

-0.62

imore

-0.61

kson

-0.59

POSITIVE LOGITS

th

1.03

0.95

0.92

0.89

0.87

0.86

0.85

0.84

0.83

Activations Density 0.066%

numeric expressions in the format of time, such as hours and minutes

references to numbered locations or time codes

No Comments

No Known Activations