INDEX

Explanations

details related to specific quarters, periods, and halves in a sports game

oai_token-act-pair · gpt-3.5-turbo

references to game periods, quarters, or innings in sports contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.74

mbuds

-0.67

ITNESS

-0.66

Documents

-0.65

 Standards

-0.65

lectic

-0.64

 Canaver

-0.63

iths

-0.62

 Antiqu

-0.60

 Communities

-0.60

POSITIVE LOGITS

 inning

1.10

 baseman

0.97

 halftime

0.91

 quarter

0.89

 season

0.89

 matchup

0.85

 scoreboard

0.82

 consecutive

0.81

 league

0.79

 tier

0.79

Activations Density 0.088%

details related to specific quarters, periods, and halves in a sports game

references to game periods, quarters, or innings in sports contexts

No Comments

No Known Activations