INDEX

Explanations

numerical sequences related to sports, such as scores, time periods, and statistics

oai_token-act-pair · gpt-3.5-turbo

ordinal numbers and references to specific periods in sports events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Material

-0.74

Materials

-0.74

 RELEASE

-0.72

Images

-0.72

Commerce

-0.71

ITNESS

-0.70

apest

-0.69

Products

-0.68

 Materials

-0.68

bos

-0.68

POSITIVE LOGITS

 inning

1.05

 baseman

1.00

 playoff

0.93

 halftime

0.91

 matchup

0.87

 league

0.83

 teammate

0.82

 innings

0.82

 offensively

0.81

omore

0.81

Activations Density 0.096%

numerical sequences related to sports, such as scores, time periods, and statistics

ordinal numbers and references to specific periods in sports events

No Known Activations