INDEX

Explanations

variable references in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Hend

-0.36

 hover

-0.35

 electr

-0.35

 preached

-0.34

 biß

-0.34

 preſ

-0.34

masına

-0.34

 HOPE

-0.34

eração

-0.33

 لئے

-0.33

POSITIVE LOGITS

:✨

0.89

RegressionTest

0.78

__;

0.72

revert

0.70

 resourceCulture

0.70

 فريبيس

0.69

 للمعارف

0.63

 aDecoder

0.62

AISSEE

0.60

ValueStyle

0.59

Activations Density 0.379%

variable references in code

No Comments

No Known Activations