INDEX

Explanations

details related to television and film narratives

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

story, family, or world narratives

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

 onPostExecute

-0.43

ToServer

-0.31

vua

-0.31

KCl

-0.31

ló

-0.30

TAR

-0.30

Huy

-0.30

取

-0.30

∧

-0.29

ToProps

-0.29

POSITIVE LOGITS

 '\\;'

0.68

:✨

0.62

 lenker

0.61

 HasFactory

0.60

 CreateTagHelper

0.60

 للاسماء

0.59

NameInMap

0.58

transQ

0.55

 protoimpl

0.52

ftagPool

0.52

Activations Density 0.011%

details related to television and film narratives

story, family, or world narratives

No Comments

No Known Activations