INDEX

Explanations

sections that provide a brief summary or overview of content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

CloseOperation

-0.82

StructEnd

-0.80

 crdi

-0.79

 تضيفلها

-0.77

出版年

-0.76

 Shaksp

-0.75

 Normdatei

-0.74

ayaquil

-0.73

 Shakspeare

-0.72

 NSCoder

-0.71

POSITIVE LOGITS

 consists

0.94

 consiste

0.78

 consist

0.73

 basically

0.73

 consisted

0.72

 Basically

0.72

Basically

0.71

 polega

0.70

 суть

0.69

 involves

0.68

Activations Density 0.613%

sections that provide a brief summary or overview of content

No Comments

No Known Activations