INDEX

Explanations

soccer-related terms and names

oai_token-act-pair · gpt-3.5-turbo

proper names and numerical identifiers in the text

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

 therap

-0.79

 dens

-0.77

erning

-0.76

 tens

-0.75

 programmers

-0.73

 billions

-0.73

indust

-0.72

 thousands

-0.72

 trillions

-0.69

-0.68

POSITIVE LOGITS

 Playoffs

0.90

 Finals

0.85

 Penalty

0.85

 Wolves

0.84

 Played

0.83

 Defensive

0.82

 Offensive

0.80

 Playoff

0.80

TBA

0.79

Coach

0.77

Activations Density 0.144%

soccer-related terms and names

proper names and numerical identifiers in the text

No Comments

No Known Activations