INDEX

Explanations

references to historical buildings and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 виправивши

-0.85

Personendaten

-0.83

 AssemblyCulture

-0.80

 NSCoder

-0.78

InitVars

-0.77

رشف

-0.75

 snippetHide

-0.75

endforeach

-0.74

AndEndTag

-0.74

tagHelperRunner

-0.73

POSITIVE LOGITS

 built

0.97

 erected

0.95

 constructed

0.91

 adjacent

0.89

 renovated

0.85

 opened

0.84

 located

0.80

 designed

0.80

 adjoining

0.80

 situated

0.79

Activations Density 0.348%

references to historical buildings and structures

No Comments

No Known Activations