INDEX

Explanations

instances of enumeration or ordering

oai_token-act-pair · gpt-3.5-turbo

references to specific entries or installments in a series or franchise

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

nces

-0.76

aver

-0.72

nesses

-0.70

bos

-0.68

acon

-0.67

 spiders

-0.67

aries

-0.66

borg

-0.65

rians

-0.64

lo

-0.63

POSITIVE LOGITS

 equation

0.73

oried

0.71

 Chain

0.69

 Secondary

0.66

tein

0.65

ilyn

0.65

 Â©

0.65

_{

0.62

 saga

0.61

ģĸ

0.61

Activations Density 0.403%

instances of enumeration or ordering

references to specific entries or installments in a series or franchise

No Comments

No Known Activations