INDEX

Explanations

the word "vel" with varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

words or phrases that indicate high value or excellence

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

SHARE

-0.67

AME

-0.66

BILITIES

-0.64

EMS

-0.63

nces

-0.63

 Ended

-0.62

apple

-0.60

SAM

-0.60

 Noon

-0.60

MIS

-0.60

POSITIVE LOGITS

ocity

1.28

vel

1.06

icit

0.88

vet

0.82

ieve

0.81

iev

0.81

icular

0.80

theless

0.78

istically

0.78

edo

0.77

Activations Density 0.006%

the word "vel" with varying levels of activation

words or phrases that indicate high value or excellence

No Comments

No Known Activations