INDEX

Explanations

references to molds in industrial or manufacturing contexts

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-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

 mold

-0.85

 turnips

-0.84

 raiſ

-0.82

 uſed

-0.81

 mould

-0.81

 ſhe

-0.71

 sandstones

-0.71

 propOrder

-0.71

UseVisualStyle

-0.70

 againſt

-0.69

POSITIVE LOGITS

0.75

\}\\

0.65

."

0.57

rungsseite

0.56

 Audiodateien

0.56

Btu

0.54

 lenker

0.53

$.\\

0.52

 resourceCulture

0.52

Activations Density 0.010%

references to molds in industrial or manufacturing contexts

No Comments

No Known Activations