INDEX

Explanations

phrases associated with speculative or imaginative content

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific symbol or character

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Hil

-0.80

 miss

-0.68

 minim

-0.65

 Miss

-0.65

 Victims

-0.65

 Mill

-0.64

 Unified

-0.64

HMS

-0.64

 depress

-0.63

 Virgin

-0.63

POSITIVE LOGITS

ĺ

1.90

ĸ

1.34

Ĺ

1.29

ĭ

1.22

Ĵ

1.18

Ķ

1.16

¥

1.15

ĳ

1.15

©

1.14

ħ

1.14

Activations Density 0.105%

phrases associated with speculative or imaginative content

occurrences of a specific symbol or character

No Comments

No Known Activations