INDEX

Explanations

references to software modules or libraries

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

programming and foreign language words

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

WriteTagHelper

-0.81



-0.66

 resourceCulture

-0.61

-------------</

-0.61

transQ

-0.60

EndContext

-0.58

 betweenstory

-0.56

RegressionTest

-0.55

querque

-0.55

hiculo

-0.54

POSITIVE LOGITS

IContainer

0.53

 biß

0.34

 Pläne

0.34

import

0.32

gruß

0.32

größe

0.31

ome

0.31

LayoutStyle

0.30

 éprou

0.30

 anunciou

0.30

Activations Density 0.000%

references to software modules or libraries

programming and foreign language words

No Comments

No Known Activations