INDEX

Explanations

concepts related to secrecy and concealment

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

ValueStyle

-0.70

 initComponents

-0.67

ArgsConstructor

-0.62

tamol

-0.62

 spasm

-0.60

,:)

-0.58

MigrationBuilder

-0.58

 aload

-0.57

Lähteet

-0.56

ConstraintMaker

-0.56

POSITIVE LOGITS

 hiding

1.62

 hides

1.61

hid

1.59

 hide

1.58

 hidden

1.54

 conceal

1.53

 concealment

1.53

 concealing

1.44

 concealed

1.44

 Hiding

1.41

Activations Density 0.176%

concepts related to secrecy and concealment

No Comments

No Known Activations