INDEX

Explanations

years or dates in a specific format

oai_token-act-pair · gpt-3.5-turbo

negative expressions related to sports seasons and performance metrics

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

 Zoro

-0.71

 Dickinson

-0.69

ensor

-0.68

 scanner

-0.65

 Harmon

-0.65

 thumbs

-0.64

 Carrier

-0.63

Gim

-0.62

 moder

-0.62

 Feather

-0.61

POSITIVE LOGITS

1.18

1.17

1.16

1.14

1.12

present

1.11

1.10

Activations Density 0.037%

years or dates in a specific format

negative expressions related to sports seasons and performance metrics

No Comments

No Known Activations