INDEX

Explanations

instances of the word 'aded' with varying degrees of activation

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "adding" or "addition."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

STER

-0.68

PE

-0.63

inarily

-0.62

 pronounced

-0.60

%]

-0.57

 tremend

-0.57

hey

-0.57

ECH

-0.55

 socket

-0.55

ancial

-0.55

POSITIVE LOGITS

aded

1.33

ading

1.32

aders

0.94

ades

0.85

adoes

0.72

ader

0.70

cliffe

0.69

hani

0.66

ffiti

0.66

 blindly

0.66

Activations Density 0.008%

instances of the word 'aded' with varying degrees of activation

words related to the concept of "adding" or "addition."

No Comments

No Known Activations