INDEX

Explanations

words related to specific topics or themes, such as "themed" or "related."

oai_token-act-pair · gpt-3.5-turbo

terms that indicate a relationship to specific themes or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ometric

-0.86

AUT

-0.78

earchers

-0.77

pload

-0.76

ocative

-0.74

ruary

-0.73

atel

-0.73

ocrates

-0.72

worn

-0.72

wow

-0.71

POSITIVE LOGITS

 enterprises

0.76

lihood

0.74

 nonprofits

0.73

 compounds

0.72

 activities

0.70

 innovations

0.70

 tendencies

0.70

 initiatives

0.69

 haze

0.69

 additions

0.68

Activations Density 0.147%

words related to specific topics or themes, such as "themed" or "related."

terms that indicate a relationship to specific themes or topics

No Comments

No Known Activations