INDEX

Explanations

mathematical symbols, variables, and context related to data structures or algorithms

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

 referenties

-0.69

+#+#

-0.67

 فريبيس

-0.62

ConstraintMaker

-0.60

Geplaatst

-0.56

principalColumn

-0.53

 كومونز

-0.53

 Roskov

-0.52

enterOuterAlt

-0.51

 otomatig

-0.51

POSITIVE LOGITS

 Itself

0.63

 themselves

0.60

 itself

0.58

 olmayan

0.57

themselves

0.56

 själva

0.55

 himself

0.55

itself

0.49

 untere

0.49

himself

0.49

Activations Density 2.401%

mathematical symbols, variables, and context related to data structures or algorithms

No Comments

No Known Activations