INDEX

Explanations

punctuation and syntax elements within a code or textual structure

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

mathematical expressions with exponents

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

pos

-0.37

応援

-0.25

ver

-0.25

传

-0.24

com

-0.24

 posti

-0.24

 signaling

-0.24

mû

-0.24

了一眼

-0.24

POSITIVE LOGITS

 resourceCulture

0.85

 дописавши

0.65

 FetchType

0.65

uxxxx

0.61

AutoScaleMode

0.61

ParallelGroup

0.59

دانشنامهٔ

0.57



0.57

 BoxFit

0.57

éfono

0.57

Activations Density 0.004%

punctuation and syntax elements within a code or textual structure

mathematical expressions with exponents

No Comments

No Known Activations