INDEX

Explanations

references to controversial political figures and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

queryInterface

-0.53

apunov

-0.47

TagMode

-0.46

Portale

-0.46

IntoConstraints

-0.45

PreExecute

-0.44

 برانيه

-0.44

 AppModule

-0.44

 gén

-0.42

शल

-0.42

POSITIVE LOGITS

 kasarigan

0.92

 claiming

0.69

 BoxDecoration

0.66

MessageTagHelper

0.65

CORBA

0.65

 claimed

0.64

EDEFAULT

0.63

 blindly

0.59

 claim

0.59

 Seeder

0.58

Activations Density 0.536%

references to controversial political figures and their actions

No Comments

No Known Activations