INDEX

Explanations

numeric values and measurements

oai_token-act-pair · gpt-3.5-turbo

the presence of phrases indicating receipt of specific items or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

agate

-0.72

 cafes

-0.66

 unravel

-0.63

ventures

-0.61

 chase

-0.61

nown

-0.60

 arteries

-0.59

 eras

-0.59

istence

-0.59

 havoc

-0.59

POSITIVE LOGITS

 permission

0.77

BuyableInstoreAndOnline

0.77

 blessing

0.75

olicited

0.74

 Notice

0.74

 brunt

0.73

treatment

0.71

èĢħ

0.70

 notice

0.69

loads

0.68

Activations Density 0.235%

numeric values and measurements

the presence of phrases indicating receipt of specific items or information

No Comments

No Known Activations