INDEX

Explanations

formatting related to visual elements in a markup language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.74

UnusedPrivate

-0.73

 Monfieur

-0.72

 NSCoder

-0.72

extAlignment

-0.70

EndInit

-0.70

 Normdatei

-0.69

WriteTagHelper

-0.67

 doInBackground

-0.65

AccessorTable

-0.65

POSITIVE LOGITS

fony

0.58

"}"

0.57

codile

0.56

on

0.56

soka

0.56

phosa

0.55

idjan

0.55

ASONS

0.54

ක්

0.53

ginx

0.53

Activations Density 0.056%

formatting related to visual elements in a markup language

No Comments

No Known Activations