INDEX

Explanations

references to proximity or closeness, both in spatial and relational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

splan

-0.57

はじめに

-0.55

πω

-0.54

WebControls

-0.54

sprogramm

-0.53

innerHeight

-0.53

migrationBuilder

-0.53

 deeper

-0.52

__":

-0.52

Referências

-0.51

POSITIVE LOGITS

 proximity

0.93

 knit

0.82

knit

0.81

 quarters

0.79

 shave

0.71

 Quarters

0.70

 approximation

0.68

 Knit

0.67

 relatives

0.66

Knit

0.65

Activations Density 0.191%

references to proximity or closeness, both in spatial and relational contexts

No Comments

No Known Activations