INDEX

Explanations

code-like structures or syntax elements related to programming or object-oriented definitions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

böz

-0.69

 Zink

-0.66

腳

-0.64

ünd

-0.64

Cabe

-0.64

ква

-0.61

profen

-0.61

 Krak

-0.61

Getenv

-0.60

 pres

-0.59

POSITIVE LOGITS

:::

1.33

::

1.08

::{

1.03

::

0.99

:::

0.97

(::

0.95

(&:

0.88

 religieuse

0.85

>::

0.84

>::

0.84

Activations Density 0.033%

code-like structures or syntax elements related to programming or object-oriented definitions

No Comments

No Known Activations