INDEX

Explanations

affirmative or active verbs related to actions or processes in a narrative

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

MigrationBuilder

-0.81

 betrek

-0.68

 choreographer

-0.60

 externi

-0.57

 trener

-0.56

 Infir

-0.55

Démographie

-0.55

AndEndTag

-0.55

 بيها

-0.54

POSITIVE LOGITS

 blogging

0.92

 filming

0.87

 hunting

0.86

 drumming

0.86

 gardening

0.85

 farming

0.85

 drinking

0.83

 partying

0.82

 shooting

0.82

 editing

0.81

Activations Density 0.385%

affirmative or active verbs related to actions or processes in a narrative

No Comments

No Known Activations