INDEX

Explanations

references to code, mathematical notation, and data structures

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

mathematical or code references

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

 fine

-0.39

 multi

-0.38

 serious

-0.37

-0.35

 senior

-0.34

bi

-0.33

 Persson

-0.33

“

-0.32

rev

-0.32

 permanent

-0.32

POSITIVE LOGITS

IsContent

0.82

PerformLayout

0.67

RenderAtEndOf

0.66

ſammen

0.66

 Vikipedi

0.63

featureID

0.61

 EconPapers

0.60

 queſto

0.60

antası

0.59

 ويكيپ

0.58

Activations Density 0.347%

references to code, mathematical notation, and data structures

mathematical or code references

No Comments

No Known Activations