INDEX

Explanations

actions involving manipulation or interaction with objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SequentialGroup

-0.70

 Majefty

-0.56

ſelves

-0.55

ActivityResult

-0.54

erapeu

-0.54

Kec

-0.54

\{\\

-0.53

[*]

-0.52

 Federated

-0.52

 Megal

-0.52

POSITIVE LOGITS

لينكات

0.56

 الحره

0.56

 provisoire

0.56

reicht

0.55

hdessä

0.55

 négociations

0.52

 régl

0.52

 aussitôt

0.49

 asupra

0.49

 alluminio

0.48

Activations Density 0.456%

actions involving manipulation or interaction with objects

No Comments

No Known Activations