INDEX

Explanations

expressions related to conditional checks and variable assessments within code

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

]=>

-0.57

Lähteet

-0.52

setVerticalGroup

-0.51

__':

-0.50

ResumeLayout

-0.50

 Ceramby

-0.49

tvguidetime

-0.47

RegressionTest

-0.46

 Felix

-0.46

 препратки

-0.44

POSITIVE LOGITS

AxisAlignment

0.66

 quidem

0.61

 StringTokenizer

0.60

리가

0.60

FetchType

0.54

ใด

0.54

 fizer

0.54

ficulty

0.53

PhysRevD

0.52

 weren

0.52

Activations Density 0.379%

expressions related to conditional checks and variable assessments within code

No Comments

No Known Activations