INDEX

Explanations

mentions of specific actions or descriptors that evoke a strong response

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 myſelf

-0.98

 itſelf

-0.85

 Majefty

-0.82

 Monfieur

-0.81

 ſeveral

-0.79

 AttributeSet

-0.76

الحياه

-0.76

 himſelf

-0.74

 ་་

-0.74

 fubject

-0.74

POSITIVE LOGITS

me

0.65

us

0.59

our

0.45

0.44

 hanem

0.43

Me

0.40

0.39

 saites

0.39

0.37

di

0.36

Activations Density 0.385%

mentions of specific actions or descriptors that evoke a strong response

No Comments

No Known Activations