INDEX

Explanations

documentation-style comments and annotation indicators in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AsUp

-0.64

 —,

-0.57

abspath

-0.57

достатки

-0.54

oprot

-0.54

istani

-0.54

 согласи

-0.54

 Infórmanos

-0.54

basicConfig

-0.53

spesies

-0.53

POSITIVE LOGITS

///

0.98

///

0.97

///<

0.75

0.68

soever

0.66

/////

0.65

AndEndTag

0.63

 Kär

0.62

\\\

0.61

\\\

0.61

Activations Density 0.030%

documentation-style comments and annotation indicators in code

No Comments

No Known Activations