INDEX

Explanations

references to rankings or standings within sports leagues

oai_token-act-pair · gpt-3.5-turbo

references to a competitive sports league

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EStream

-0.86

imura

-0.69

anamo

-0.69

etsk

-0.67

«

-0.67

 Virtue

-0.66

ihara

-0.66

 Liberties

-0.65

 Rider

-0.65

imaru

-0.65

POSITIVE LOGITS

 standings

0.77

average

0.75

wide

0.75

 playoffs

0.73

 commissioner

0.73

 chang

0.73

 Scouting

0.72

oster

0.72

 championships

0.71

 lockout

0.68

Activations Density 0.019%

references to rankings or standings within sports leagues

references to a competitive sports league

No Comments

No Known Activations