INDEX

Explanations

mathematical terms and calculations related to combinatorial structures and probabilities

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

number of ways

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

AndEndTag

-0.58

antası

-0.57

 المعيارى

-0.56

contentLoaded

-0.50

#+#

-0.50

pointments

-0.49

writeFieldEnd

-0.47

dafx

-0.46

BeginContext

-0.46

findpost

-0.46

POSITIVE LOGITS

RunWith

0.46

évaluateur

0.40

 solidity

0.40

Linq

0.39

copyFrom

0.37

 reuters

0.36

 solid

0.36

 sare

0.36

GD

0.35

Ruben

0.35

Activations Density 0.450%

mathematical terms and calculations related to combinatorial structures and probabilities

number of ways

No Comments

No Known Activations