INDEX

Explanations

negative affirmations or expressions of doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 coherence

-0.64

 gyhoeddwyd

-0.62

éc

-0.59

 grossesse

-0.58

 unum

-0.57

 splendour

-0.57

 pollination

-0.56

Coll

-0.55

 Hins

-0.55

mathit

-0.55

POSITIVE LOGITS

+#+

0.77

tvguidetime

0.76

ViewInit

0.72

]]

0.65

 Himo

0.64

};*/

0.63

Initializable

0.63

TestingModule

0.63

 lenker

0.62

 intptr

0.62

Activations Density 0.123%

negative affirmations or expressions of doubt

No Comments

No Known Activations