INDEX

Explanations

references to various types or categories

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

cshtml

-0.60

 Pública

-0.59

 supernat

-0.55

 résoudre

-0.55

appcompat

-0.52

 Ambiental

-0.51

 EconPapers

-0.51

upné

-0.51

 lombok

-0.49

 religione

-0.49

POSITIVE LOGITS

 getType

0.99

 Type

0.98

 types

0.97

 type

0.96

 Types

0.91

 TYPE

0.84

Typ

0.83

 setType

0.82

stype

0.81

typ

0.79

Activations Density 0.349%

references to various types or categories

No Comments

No Known Activations