INDEX

Explanations

references to films and movies

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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 inmun

-0.55

 groen

-0.54

tonsoft

-0.54

etragen

-0.51

ävän

-0.51

interesse

-0.49

 arché

-0.49

 attes

-0.49

нтів

-0.48

 petto

-0.47

POSITIVE LOGITS

 film

2.93

 movie

2.79

 Film

2.72

film

2.66

 films

2.65

 movies

2.61

Film

2.60

 Movie

2.55

movie

2.51

Movie

2.46

Activations Density 0.119%

references to films and movies

No Comments

No Known Activations