INDEX

Explanations

references to authors and publication details in academic or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 propOrder

-0.65

esus

-0.64

erecht

-0.63

mmHg

-0.61

///

-0.61

webElementXpaths

-0.58

gione

-0.58

ποτε

-0.58

Condol

-0.57



-0.56

POSITIVE LOGITS

APD

0.81

 Amat

0.77

 különböz

0.77

رشف

0.76

Aos

0.74

SuppressLint

0.74

 Arundel

0.73

 ActivatedRoute

0.72

Aps

0.72

AutoScaleMode

0.71

Activations Density 3.189%

references to authors and publication details in academic or scientific contexts

No Comments

No Known Activations