INDEX

Explanations

elements related to actions and physical interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Base

-0.49

 tramite

-0.44

Way

-0.42

Via

-0.41

 modo

-0.41

事で

-0.41

途中

-0.40

lapses

-0.40

GenerationType

-0.40

付け

-0.39

POSITIVE LOGITS

 '\\;'

0.90

arraycopy

0.88

ScopeManager

0.87

 saites

0.84

ChildScrollView

0.80

 loudest

0.78

jsonwebtoken

0.76

 greener

0.76

 smiling

0.75

 ***!

0.74

Activations Density 0.363%

elements related to actions and physical interactions

No Comments

No Known Activations