INDEX

Explanations

terms related to programming functions and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

PROP

-0.39

 typelib

-0.37

WebElementEntity

-0.35

 Cameron

-0.34

onActivityResult

-0.33

deepEqual

-0.33

accesso

-0.32

邦

-0.32

NSDictionary

-0.31

propy

-0.31

POSITIVE LOGITS

openzeppelin

0.60

leſs

0.56

CppCodeGen

0.56

ftagPool

0.56

ſelves

0.53

InjectAttribute

0.52

 nakalista

0.52

featureID

0.51

ſelf

0.51

 kasarigan

0.51

Activations Density 0.161%

terms related to programming functions and data structures

No Comments

No Known Activations