INDEX

Explanations

mathematical notations or symbols typically used in equations or expressions

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

GEBURTSDATUM

-1.53

Efq

-1.52

 Jefus

-1.45

 itſelf

-1.39

 myſelf

-1.37

 pleaſure

-1.36

 AssemblyCulture

-1.36

 Majefty

-1.35

principalTable

-1.35

Personendaten

-1.35

POSITIVE LOGITS

0.94

0.88

<em>

0.86

<u>

0.85

<i>

0.85

<strong>

0.85

<sup>

0.84

0.83

in

0.82

Activations Density 0.396%

mathematical notations or symbols typically used in equations or expressions

No Comments

No Known Activations