INDEX

Explanations

phrases related to limitations and constraints

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

following specific phrases

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

 AssemblyCompany

-0.74

Jîn

-0.58

EDEFAULT

-0.58

CloseOperation

-0.56

رشف

-0.56

GraphicsUnit

-0.56

 BoxDecoration

-0.53



-0.52

DebuggerNonUser

-0.51

 tartalomajánló

-0.51

POSITIVE LOGITS

 congi

0.37

仕方

0.37

 נח

0.33

ResourceType

0.33

 spare

0.32

estre

0.31

 estre

0.31

 tunn

0.31

halb

0.30

werben

0.30

Activations Density 0.267%

phrases related to limitations and constraints

following specific phrases

No Comments

No Known Activations