INDEX

Explanations

references to actions or changes in roles and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 protoimpl

-0.66

 propOrder

-0.65

TagMode

-0.65

findpost

-0.62

VersionUID

-0.60

onViewCreated

-0.59

cci

-0.58

 كومونز

-0.58

*/].

-0.56

^(@

-0.56

POSITIVE LOGITS

 again

3.06

again

2.80

Again

2.79

 Again

2.71

 AGAIN

2.31

 novamente

2.28

 nuevamente

2.15

 опять

2.02

 opět

1.97

 снова

1.88

Activations Density 0.942%

references to actions or changes in roles and responsibilities

No Comments

No Known Activations