INDEX

Explanations

references to action, significance, or questions related to personal experiences and agency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 wireType

-0.71

RefNanny

-0.69

 dAtA

-0.65

NESDAY

-0.61

 مواليد

-0.59

 Normdatei

-0.57

,:),

-0.57

bleshooting

-0.56

ARDO

-0.55

 propOrder

-0.54

POSITIVE LOGITS

 historiques

0.61

$__

0.58

 dimaksud

0.58

 öyle

0.56

 justement

0.53

 chrétienne

0.52

 fapt

0.52

 trattano

0.52

 precisamente

0.52

 heureuse

0.52

Activations Density 0.668%

references to action, significance, or questions related to personal experiences and agency

No Comments

No Known Activations