INDEX

Explanations

terms related to electronic properties and devices

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.92

 ſever

-0.78

 étoit

-0.77

 houſe

-0.75

 morire

-0.75

 HasFactory

-0.74

 ſtate

-0.74

 themſelves

-0.72

 FishBase

-0.72

 Conſ

-0.71

POSITIVE LOGITS

 electronic

0.93

electronic

0.90

Electronic

0.79

 Electronic

0.78

 electronics

0.77

 elektron

0.76

elektron

0.75

 stream

0.72

electronics

0.69

 elektronik

0.66

Activations Density 0.112%

terms related to electronic properties and devices

No Comments

No Known Activations