INDEX

Explanations

references to a specific technology or product, particularly related to integrated circuits

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

AlterField

-1.13

 myſelf

-1.01

LookAnd

-1.01

Efq

-1.00

 itſelf

-0.98

sizeCache

-0.97

 يتيمه

-0.97

 Theſe

-0.97

 JMenuItem

-0.96

antMatchers

-0.95

POSITIVE LOGITS

 method

0.81

 described

0.76

<eos>

0.73

0.68

 Full

0.66

ella

0.64

<code>

0.63

Full

0.61

↵↵

0.59

 mentioned

0.56

Activations Density 0.175%

references to a specific technology or product, particularly related to integrated circuits

No Comments

No Known Activations