INDEX

Explanations

mentions of the year 2013

oai_token-act-pair · gpt-3.5-turbo

references to the year 2013

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

flo

-0.84

warts

-0.72

sembly

-0.72

bip

-0.70

 thous

-0.69

kef

-0.68

srf

-0.67

phy

-0.66

 ship

-0.66

merce

-0.65

POSITIVE LOGITS

å¹

0.91

-'

0.84

 onwards

0.82

rd

0.72

 INTER

0.71

 edition

0.71

bard

0.70

 onward

0.69

0.68

 Definition

0.68

Activations Density 0.050%

mentions of the year 2013

references to the year 2013

No Comments

No Known Activations