INDEX

Explanations

words related to pitching and throwing in a sports context

oai_token-act-pair · gpt-3.5-turbo

terms related to throwing and pitch in a sports context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Starship

-0.77

AFTA

-0.75

 apost

-0.74

atis

-0.73

 Gent

-0.70

 Nasa

-0.69

 Malays

-0.69

 Orwell

-0.69

DragonMagazine

-0.67

 Acer

-0.67

POSITIVE LOGITS

otherapy

0.87

 velocity

0.83

ansas

0.83

 batted

0.80

 coached

0.75

 rehab

0.74

 coach

0.73

 blocker

0.72

weed

0.72

yards

0.71

Activations Density 0.054%

words related to pitching and throwing in a sports context

terms related to throwing and pitch in a sports context

No Comments

No Known Activations