INDEX

Explanations

affirmative responses or expressions of agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

`).

-0.84

munk

-0.81

']").

-0.81

".

-0.80

%");

-0.80

'>"

-0.80

=")

-0.80

*/}

-0.79

();*/

-0.79

')]

-0.79

POSITIVE LOGITS

Yes

2.12

yes

2.05

Yes

2.04

YES

2.02

yes

1.99

YES

1.94

YesNo

1.20

Yess

1.18

Sí

1.08

Sì

1.07

Activations Density 0.054%

affirmative responses or expressions of agreement

No Comments

No Known Activations