INDEX

Explanations

mentions of physical or mental activities related to improvement or practice

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "exercise."

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

gets

-0.76

fixed

-0.66

alty

-0.66

lines

-0.65

Dak

-0.64

ymes

-0.63

apper

-0.61

appers

-0.60

 porous

-0.60

bi

-0.59

POSITIVE LOGITS

ercise

1.08

 exerc

1.04

 exercise

1.02

 exercises

0.96

orius

0.91

 Exercise

0.91

 routines

0.80

 regimen

0.80

ç·

0.77

issance

0.76

Activations Density 0.009%

mentions of physical or mental activities related to improvement or practice

occurrences of the word "exercise."

No Comments

No Known Activations