INDEX

Explanations

numerical data and results

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

sentence terminators

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

 transfieras

-0.89

 насељу

-0.74

AndEndTag

-0.69

 ſta

-0.66

يكب

-0.66

NameInMap

-0.62

RenderAtEndOf

-0.61

webElementXpaths

-0.61

 desmotivaciones

-0.59

 '\\;'

-0.59

POSITIVE LOGITS

lash

0.38

 refroidissement

0.36

стру

0.35

 ARISING

0.34

もしろ

0.34

 whil

0.32

 COOL

0.32

pass

0.32

Boc

0.32

pec

0.31

Activations Density 0.240%

numerical data and results

sentence terminators

No Comments

No Known Activations