INDEX

Explanations

phrases indicating movement or direction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tvguidetime

-0.79

 AssemblyCulture

-0.71

ścioła

-0.51

 resourceCulture

-0.51

 виправивши

-0.49

 MediatR

-0.48

FTFY

-0.48

äsident

-0.47

<()>

-0.47

èdia

-0.46

POSITIVE LOGITS

 Into

0.77

Entering

0.77

 entering

0.75

 Entering

0.73

 enters

0.73

 memasuki

0.71

Into

0.70

 entered

0.69

entering

0.68

 INTO

0.67

Activations Density 0.248%

phrases indicating movement or direction

No Comments

No Known Activations