INDEX

Explanations

template literals or string interpolation syntax in code

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

string interpolation with backticks and dollar signs

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

uxxxx

-0.65

 ſche

-0.61

 ſch

-0.61

 faſt

-0.61

 CreateTagHelper

-0.59

 houſe

-0.56

 betweenstory

-0.56

 Houſe

-0.56

 ſta

-0.55

 resultList

-0.54

POSITIVE LOGITS

($"{

0.61

your

0.59

(`${

0.58

WriteTagHelper

0.56

/${

0.55

={`${

0.52

`${

0.52

0.51

 your

0.51

orElseThrow

0.51

Activations Density 0.002%

template literals or string interpolation syntax in code

string interpolation with backticks and dollar signs

No Comments

No Known Activations