INDEX

Explanations

dates and team names related to sports events

oai_token-act-pair · gpt-3.5-turbo

numeric representations and scores related to sports events

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

 vigilant

-0.63

 Hert

-0.62

TJ

-0.62

RTX

-0.62

 wait

-0.60

 pseudo

-0.59

 webcam

-0.58

Jem

-0.57

 thirty

-0.57

 countdown

-0.57

POSITIVE LOGITS

1.33

1.31

1.25

1.24

1.20

1.15

1.12

1.10

Activations Density 0.070%

dates and team names related to sports events

numeric representations and scores related to sports events

No Comments

No Known Activations