INDEX

Explanations

words related to conversion processes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 geladeira

-0.49

 olvid

-0.47

RDONLY

-0.47

auré

-0.47

 rutina

-0.47

 pathlib

-0.46

 InputDecoration

-0.46

 sentado

-0.46

hashCode

-0.46

 tabindex

-0.45

POSITIVE LOGITS

 conversion

4.49

 Conversion

4.24

 conversions

4.02

 convert

3.99

 converted

3.89

Conversion

3.87

conversion

3.86

 converting

3.82

 converts

3.66

 Conversions

3.54

Activations Density 0.103%

words related to conversion processes in various contexts

No Comments

No Known Activations