INDEX

Explanations

programming constructs related to function definitions and method calls

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

coach at

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

PerformLayout

-0.65

TagMode

-0.54

 feroit

-0.48

ंदीखरीदारी

-0.48

 faſt

-0.48

 compéti

-0.45

 desmotivaciones

-0.44

 auttaa

-0.44

Efq

-0.44

 étoient

-0.43

POSITIVE LOGITS

RSpec

0.49

ilen

0.46

]")]

0.45

JspWriter

0.42

iving

0.42

 StringBuilder

0.42

 endforeach

0.42

marino

0.41

 azért

0.41

aken

0.41

Activations Density 0.056%

programming constructs related to function definitions and method calls

coach at

No Comments

No Known Activations