INDEX

Explanations

phrases related to exerting effort or control over a particular situation or domain

oai_token-act-pair · gpt-3.5-turbo

references to running or managing activities and associated risks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ema

-0.79

ayers

-0.78

iatus

-0.73

orrow

-0.72

tymology

-0.69

gdala

-0.66

Artist

-0.63

ESA

-0.63

 Chomsky

-0.63

oult

-0.62

POSITIVE LOGITS

 smoothly

1.06

 simulations

0.96

auntlet

0.90

err

0.88

gam

0.86

 affairs

0.83

 efficiently

0.83

 risk

0.81

 marathon

0.80

 tests

0.79

Activations Density 0.095%

phrases related to exerting effort or control over a particular situation or domain

references to running or managing activities and associated risks

No Comments

No Known Activations