INDEX

Explanations

names or terms with "Schm" followed by a character or set of characters

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'm'

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

Not in Any Lists

No Comments

Negative Logits

EStream

-0.72

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.70

DragonMagazine

-0.63

 pitch

-0.63

*/(

-0.62

iP

-0.62

gerald

-0.61

irtual

-0.61

IBLE

-0.61

 foul

-0.60

POSITIVE LOGITS

ichael

1.20

otor

1.20

ormon

1.16

asonry

1.14

asonic

1.13

obil

1.12

useum

1.11

obiles

1.09

ortal

1.08

aiden

1.07

Activations Density 0.057%

names or terms with "Schm" followed by a character or set of characters

occurrences of the letter 'm'

No Comments

No Known Activations