INDEX

Explanations

class and method definitions in coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ValueStyle

-0.70

WriteTagHelper

-0.65

 intptr

-0.60

RegressionTest

-0.59

 TAMBÉM

-0.58

lably

-0.57

$^\

-0.56

 AssemblyCulture

-0.56

\#\#

-0.56

ètement

-0.55

POSITIVE LOGITS

set

0.57

 היתה

0.51

(){}

0.47

 next

0.47

الدراسه

0.46

 differ

0.46

 attach

0.45

cepto

0.45

 Hutton

0.44

Activations Density 0.092%

class and method definitions in coding contexts

No Comments

No Known Activations