INDEX

Explanations

occurrences of a specific numeric or versioning format

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

`<start_of_turn>user`

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 desmotivaciones

-0.59

NamedQueries

-0.54

ьажоргаш

-0.53

 wikipagina

-0.52

 Inscrivez

-0.49



-0.49

colgante

-0.49

 increí

-0.48

CloseOperation

-0.47

 masukan

-0.47

POSITIVE LOGITS

0.53

 nakalista

0.45

Билгалдахарш

0.43

 CreateTagHelper

0.42

比特派

0.42

AndEndTag

0.41

-%

0.40

{~

0.40

="-

0.39

("/:

0.39

Activations Density 0.000%

occurrences of a specific numeric or versioning format

`<start_of_turn>user`

No Comments

No Known Activations