INDEX

Explanations

occurrences of the term "doc" and references to documentation elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

DeleteBehavior

-0.69

bleiben

-0.56

principalTable

-0.55

glDelete

-0.55

IonicModule

-0.54

 cavalli

-0.52

vited

-0.52

 almost

-0.51

िल्

-0.50

 Monfieur

-0.50

POSITIVE LOGITS

doc

1.02

MemoryWarning

0.87

doc

0.72

+:+

0.69

//

0.64

readLine

0.63

createStatement

0.62

hyrchwyd

0.61

نگار

0.61

 VIDEOTAPE

0.61

Activations Density 0.044%

occurrences of the term "doc" and references to documentation elements

No Comments

No Known Activations