INDEX

Explanations

expressions related to affirmations and existence

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

GEBURTSDATUM

-0.98

RenderAtEndOf

-0.95

tagHelperRunner

-0.83

évaluateur

-0.75

 ModelExpression

-0.73

 CreateTagHelper

-0.73

featureID

-0.69

AndEndTag

-0.69

rovnik

-0.68

 Roskov

-0.67

POSITIVE LOGITS

 another

0.89

 equivalent

0.73

 preferable

0.72

 akin

0.72

0.71

another

0.68

 part

0.67

 advantageous

0.66

Another

0.66

 beneficial

0.66

Activations Density 0.516%

expressions related to affirmations and existence

No Comments

No Known Activations