INDEX

Explanations

special characters and formatting typically used in documentation or programming

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

-0.56

<eos>

-0.54

Che

-0.45

↵

-0.45

…

-0.45

 actually

-0.45

-0.44

Mo

-0.43

 where

-0.43

Mo

-0.43

POSITIVE LOGITS

StoryboardSegue

0.99

WebVitals

0.91

 doInBackground

0.88

WriteBarrier

0.88

StringCopy

0.80

djangoproject

0.79

 HasFactory

0.79

 Roskov

0.78

](#

0.78

 pinulongan

0.77

Activations Density 0.138%

special characters and formatting typically used in documentation or programming

No Comments

No Known Activations