INDEX

Explanations

references to binary data sizes and types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

DockStyle

-0.58

DeleteBehavior

-0.53

 Thinking

-0.51

 courtesy

-0.51

 empre

-0.50

principalTable

-0.49

 basi

-0.49

Teles

-0.48

edere

-0.48

ViewStyle

-0.48

POSITIVE LOGITS

 bits

0.99

Bit

0.88

bit

0.85

 Bits

0.77

Bit

0.75

LEncoder

0.72

 BITS

0.70

bited

0.66

INSTANCE

0.65

odeon

0.64

Activations Density 0.121%

references to binary data sizes and types

No Comments

No Known Activations