INDEX

Explanations

function definitions and parameters in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

();)

-0.67

,:);

-0.63

IsContent

-0.61

,:),

-0.58

NameInMap

-0.57

 "..\..\

-0.57

]>=

-0.56

 coti

-0.54

Geographie

-0.54

CWE

-0.54

POSITIVE LOGITS

 giuri

0.50

InstanceState

0.48

 truff

0.44

AndroidJUnit

0.44

 saisir

0.43

rø

0.43

 puissance

0.42

yyq

0.42

ismiss

0.42

Calls

0.42

Activations Density 0.121%

function definitions and parameters in code

No Comments

No Known Activations