INDEX

Explanations

terms related to the word "clear."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Clear" and its variations in different contexts

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

ITAL

-0.82

ãĥĦ

-0.76

INTER

-0.71

 mockery

-0.71

 brut

-0.70

LAB

-0.69

minecraft

-0.69

LI

-0.68

alez

-0.68

 exqu

-0.66

POSITIVE LOGITS

 Clear

1.23

Clear

1.22

ance

1.00

ances

0.92

 Seal

0.87

clear

0.86

Flag

0.81

flag

0.76

 Skies

0.75

opsis

0.74

Activations Density 0.013%

terms related to the word "clear."

instances of the word "Clear" and its variations in different contexts

No Comments

No Known Activations