INDEX

Explanations

terms related to striking or hitting actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 שוליים

-0.64

ValueStyle

-0.63

 reactivity

-0.62

-0.59

 fumée

-0.57

 acontec

-0.57

 sposo

-0.56

 maïs

-0.56

 chromatin

-0.55

 accessions

-0.55

POSITIVE LOGITS

 struck

0.83

 strike

0.82

 strikes

0.81

}<\

0.80

enti

0.75

<\

0.69

ArrowToggle

0.66

rungsseite

0.65

)<\

0.63

<-

0.63

Activations Density 0.364%

terms related to striking or hitting actions

No Comments

No Known Activations