INDEX

Explanations

elements related to gaps in information or data

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

Portail

-0.72

rawDesc

-0.69

 AssemblyProduct

-0.57

 nahilalakip

-0.56

сылкі

-0.55

PostInfinity

-0.53

coltà

-0.52

发表于

-0.51

 onAnimation

-0.51

 iNdEx

-0.50

POSITIVE LOGITS

 gaps

2.07

 missing

1.95

gap

1.89

 Gaps

1.81

gaps

1.72

missing

1.71

 Missing

1.63

Missing

1.61

Gap

1.59

gap

1.59

Activations Density 0.839%

elements related to gaps in information or data

No Comments

No Known Activations