INDEX

Explanations

code snippets related to data handling and processing functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

SourceChecksum

-0.89

TagMode

-0.68

̸

-0.57

 respectively

-0.55

 alternately

-0.54

fører

-0.54

astéro

-0.54

 interrupted

-0.52

 resourceCulture

-0.52

astify

-0.52

POSITIVE LOGITS

 AssemblyCulture

0.65

 propOrder

0.62

hopal

0.53

 &___

0.52

 Waray

0.51

hemiah

0.49

mesg

0.47

 forState

0.47

centralwidget

0.47

minos

0.47

Activations Density 0.311%

code snippets related to data handling and processing functions

No Comments

No Known Activations