INDEX

Explanations

phrases that express causality or the basis for something, particularly using the word "for."

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

 Paglinawan

-0.76

 propOrder

-0.68

PerformLayout

-0.63

 snippetHide

-0.63

enteuer

-0.63

fiya

-0.61

 AssemblyTitle

-0.60

ImageContext

-0.59

simpleType

-0.59

 الحره

-0.58

POSITIVE LOGITS

por

0.96

Por

0.94

по

0.91

Por

0.84

por

0.83

По

0.81

 по

0.81

 По

0.73

 blame

0.64

ПО

0.63

Activations Density 0.137%

phrases that express causality or the basis for something, particularly using the word "for."

No Comments

No Known Activations