INDEX

Explanations

mentions of specific individuals, particularly in political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 ejus

-0.82

Edi

-0.80

Eſ

-0.77

Edi

-0.76

 Estrada

-0.75

 Elias

-0.75

 eletrônico

-0.74

 Easton

-0.73

ethane

-0.72

Ede

-0.70

POSITIVE LOGITS

AccessFile

0.78

Bli

0.73

getColumnIndex

0.72

 CreateTagHelper

0.71

Azur

0.70

omores

0.68

RunAsync

0.68

 postIndex

0.68

]{\

0.66

榊

0.66

Activations Density 1.568%

mentions of specific individuals, particularly in political contexts

No Comments

No Known Activations