INDEX

Explanations

words related to professional baseball, specifically focusing on hitters

oai_token-act-pair · gpt-3.5-turbo

terms related to baseball players and their performance, particularly hitters and batters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

iment

-0.86

rip

-0.76

legate

-0.72

region

-0.71

cess

-0.71

ional

-0.70

mental

-0.70

¥µ

-0.69

qual

-0.69

Asia

-0.69

POSITIVE LOGITS

 hitters

1.29

 batters

1.18

 hitter

1.14

 batted

0.99

 batting

0.95

 pitchers

0.90

 batter

0.87

 pitches

0.86

 reliever

0.84

 bowling

0.80

Activations Density 0.010%

words related to professional baseball, specifically focusing on hitters

terms related to baseball players and their performance, particularly hitters and batters

No Comments

No Known Activations