INDEX

Explanations

contexts related to cause and effect

oai_token-act-pair · gpt-3.5-turbo

phrases related to health outcomes and preventative measures

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

ippi

-0.75

arc

-0.73

 eyebrow

-0.72

aurus

-0.71

pport

-0.68

ãĥĬ

-0.67

achelor

-0.65

SON

-0.65

abus

-0.65

 accuse

-0.65

POSITIVE LOGITS

 exposure

0.80

 ingestion

0.80

 ingest

0.79

inh

0.75

 careful

0.73

 consuming

0.72

 supplementation

0.72

 combining

0.71

 untreated

0.70

 neglect

0.70

Activations Density 0.814%

contexts related to cause and effect

phrases related to health outcomes and preventative measures

No Comments

No Known Activations