INDEX

Explanations

references to different types of layers in a semiconductor device context

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

<eos>

-0.69

in

-0.61

-0.57

-0.56

und

-0.55

-0.54

fel

-0.54

↵↵

-0.54

POSITIVE LOGITS

 myſelf

1.30

Efq

1.24

 raiſ

1.21

 Monfieur

1.13

ſelf

1.12

 Jefus

1.12

 Anſ

1.12

 ſind

1.08

 Houſe

1.05

ſelves

1.05

Activations Density 0.130%

references to different types of layers in a semiconductor device context

No Comments

No Known Activations