INDEX

Explanations

specific identifier strings within a dataset or structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

mybatisplus

-1.02

AsUp

-0.96

 surla

-0.91

ArrowToggle

-0.88

 Wikimedijinoj

-0.84

InitVars

-0.80

fillType

-0.79

 <=",

-0.79

windowFixed

-0.78

 trajets

-0.77

POSITIVE LOGITS

source

1.16

 source

0.80

Source

0.79

<h2>

0.62

↵

0.60

“

0.59

 Source

0.58

<h1>

0.57

<strong>

0.57

SOURCE

0.56

Activations Density 0.021%

specific identifier strings within a dataset or structured format

No Comments

No Known Activations