INDEX

Explanations

references to isolated elements or conditions 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 @ 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

 Familienname

-0.60

 AssemblyTitle

-0.59

cionario

-0.57

iece

-0.56

 Förder

-0.55

 Cruces

-0.52

ourdes

-0.52

ITIONAL

-0.52

DrawerToggle

-0.52

יצוני

-0.52

POSITIVE LOGITS

WEBPACK

0.88

 skull

0.64

SQL

0.61

 constituents

0.60

 Skull

0.59

isolated

0.58

 isolated

0.57

 tunt

0.57

 oublié

0.56

text

0.56

Activations Density 0.097%

references to isolated elements or conditions in various contexts

No Comments

No Known Activations