INDEX

Explanations

terms related to significant improvements or successful performances

oai_token-act-pair · gpt-3.5-turbo

references to significant and notable achievements or performances

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

zanne

-0.81

lled

-0.80

anamo

-0.79

lessness

-0.78

anto

-0.74

lessly

-0.71

poral

-0.71

ternity

-0.71

ihil

-0.71

anium

-0.70

POSITIVE LOGITS

 breakout

1.31

draft

1.01

SpaceEngineers

0.86

WER

0.79

PsyNetMessage

0.74

brook

0.70

OWS

0.70

plot

0.69

 traject

0.68

ptions

0.67

Activations Density 0.006%

terms related to significant improvements or successful performances

references to significant and notable achievements or performances

No Comments

No Known Activations