INDEX

Explanations

references to descriptions and their associated descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

NewGuid

-0.70

thenReturn

-0.69

 realize

-0.65

IBarButtonItem

-0.64

ConfigureAwait

-0.64

andaş

-0.62

 realizing

-0.61

 Audiodateien

-0.60

preuves

-0.60

pidou

-0.58

POSITIVE LOGITS

 descriptions

0.68

SpringBootTest

0.67

 تانيه

0.67

("")]

0.65

velser

0.63

 Describes

0.63

Santis

0.62

 descri

0.62

 jLabel

0.62

 Scribd

0.61

Activations Density 0.079%

references to descriptions and their associated descriptors

No Comments

No Known Activations