INDEX

Explanations

key phrases, conjunctions, and transitional words typically used in formal writing and logical arguments

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

introductions to explanations or examples

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

IntoConstraints

-0.43

 containing

-0.39

ris

-0.38

 handler

-0.38

 growth

-0.37

 model

-0.37

 compliance

-0.37

 Scherer

-0.37

 Cunningham

-0.36

 Hand

-0.35

POSITIVE LOGITS

ंदीखरीदारी

0.64

OGND

0.59

uxxxx

0.56

rungsseite

0.56

 surla

0.51

 صوتيه

0.51

ValueStyle

0.50



0.50

DebuggerNonUser

0.49

IsMutable

0.49

Activations Density 0.231%

key phrases, conjunctions, and transitional words typically used in formal writing and logical arguments

introductions to explanations or examples

No Comments

No Known Activations