INDEX

Explanations

references to physical sensations and body parts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 debout

-0.55

::~

-0.51

ichtig

-0.46

 assise

-0.46

 occurs

-0.46

fread

-0.45

кан

-0.44

 estud

-0.43

 otur

-0.43

 censo

-0.42

POSITIVE LOGITS

protoimpl

0.78

AddTagHelper

0.76

 FetchType

0.69

Дереккөздер

0.68

 protoimpl

0.68

 BorderRadius

0.68

IntoConstraints

0.67

 saites

0.66

 twitch

0.66

AndroidJUnit

0.66

Activations Density 0.181%

references to physical sensations and body parts

No Comments

No Known Activations