INDEX

Explanations

instances of the word "improve"

oai_token-act-pair · gpt-3.5-turbo

terms related to improvement or enhancement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Straw

-0.78

itto

-0.77

cium

-0.72

NetMessage

-0.71

cia

-0.70

ansas

-0.69

beck

-0.66

pull

-0.65

runners

-0.64

ãĥĪ

-0.64

POSITIVE LOGITS

ments

0.88

 efficiency

0.83

 markedly

0.80

 productivity

0.79

 acquainted

0.78

 responsiveness

0.77

iets

0.77

 materially

0.75

iating

0.75

 exponentially

0.74

Activations Density 0.041%

instances of the word "improve"

terms related to improvement or enhancement

No Comments

No Known Activations