INDEX

Explanations

specific syntax or structure in code-like text

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

special characters and non-English words

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

Es

-0.40

cit

-0.38

Syl

-0.38

Syl

-0.37

cle

-0.36

 Fores

-0.36

Jaz

-0.36

Hal

-0.35

dex

-0.35

Zap

-0.35

POSITIVE LOGITS

adaptiveStyles

0.70

 faſt

0.68

 nakalista

0.66

 anún

0.63

ſelves

0.63

 snippetHide

0.62

లాలు

0.62

 ſche

0.59

 increí

0.58

__':

0.57

Activations Density 0.085%

specific syntax or structure in code-like text

special characters and non-English words

No Comments

No Known Activations