INDEX

Explanations

references to physical structures or constructions

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

fromCharCode

-0.64

basicConfig

-0.60

 larmes

-0.59

 felicità

-0.59

 poils

-0.59

JspWriter

-0.58

ResumeLayout

-0.58

فایل‌لار

-0.57

الإنجليزية

-0.56

 varandra

-0.56

POSITIVE LOGITS

 structure

1.98

 structures

1.91

Struct

1.89

 Struct

1.82

 struct

1.70

 Structures

1.66

 structuring

1.64

 Structure

1.60

structure

1.53

structures

1.52

Activations Density 0.110%

references to physical structures or constructions

No Comments

No Known Activations