INDEX

Explanations

references to libraries and data type definitions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

“

-0.89

 Pfalz

-0.84

ません

-0.78

 McMillan

-0.77

“

-0.74

 Culver

-0.74

 atos

-0.73

Def

-0.71

”

-0.70

-0.68

POSITIVE LOGITS

{~

1.64

 Gaud

0.94

ViewInit

0.94

--}}

0.92

 useCallback

0.87

wisata

0.86

 GenerationType

0.84

mallows

0.84

ultuous

0.83

"}")

0.83

Activations Density 0.122%

references to libraries and data type definitions in programming contexts

No Comments

No Known Activations