INDEX

Explanations

references to specific objects, plans, or entities within contexts of action or intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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



-1.08

ьаж

-0.91

 Administrativna

-0.89

rungsseite

-0.87

 beginnetje

-0.79

 onCreateView

-0.78

//});

-0.75

 Wikimedijinoj

-0.74

JNIEnv

-0.73

Hentet

-0.73

POSITIVE LOGITS

put

1.02

Put

0.84

Put

0.83

 puts

0.80

put

0.80

 putting

0.75

putting

0.75

Putting

0.72

 Putting

0.71

PUT

0.69

Activations Density 0.058%

references to specific objects, plans, or entities within contexts of action or intention

No Comments

No Known Activations