INDEX

Explanations

specific details and instances related to cases or occurrences in various contexts

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

case study or legal case

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

Enllaces

-0.39

ScopeManager

-0.38

 kasarigan

-0.33

jsonwebtoken

-0.32

AutoModerator

-0.32

 förr

-0.32

__':

-0.32

 nemus

-0.32

וויק

-0.31

arrol

-0.31

POSITIVE LOGITS

decision

0.55

دانشنامهٔ

0.54

ReusableCell

0.51

intios

0.49

 DECISION

0.48

Decision

0.46

 decision

0.46



0.44

Retail

0.44

 quæ

0.42

Activations Density 0.077%

specific details and instances related to cases or occurrences in various contexts

case study or legal case

No Comments

No Known Activations