INDEX

Explanations

terms related to legs or leg-related actions

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

 dumne

-0.59

 Etats

-0.55

 morts

-0.54

 disposição

-0.53

tabol

-0.53

 yaşam

-0.53

 sogni

-0.53

 ettei

-0.52

 perfeita

-0.52

 diseñada

-0.52

POSITIVE LOGITS

leg

1.09

Contracts

0.84

IndentedString

0.77

 legs

0.75

MLLoader

0.74

 contracts

0.74

contracts

0.72

 Contracts

0.69

ImageContext

0.68

انيف

0.67

Activations Density 0.117%

terms related to legs or leg-related actions

No Comments

No Known Activations