INDEX

Explanations

symbols and syntax used in programming or scripting languages

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

fina

-0.61

ква

-0.61

fi

-0.60

 Маль

-0.60

 Oliva

-0.59

Elin

-0.58

ünd

-0.58

badi

-0.56

fürst

-0.56

POSITIVE LOGITS

::

2.12

::

1.78

:::

1.65

::{

1.55

>::

1.53

>::

1.40

(::

1.39

::$

1.33

:::

1.24

::_

1.18

Activations Density 0.067%

symbols and syntax used in programming or scripting languages

No Comments

No Known Activations