INDEX

Explanations

references to sources or insiders providing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dafx

-0.79

 Nero

-0.76

AddTagHelper

-0.73

Datuak

-0.72

MENAFN

-0.69

 оригіналу

-0.68

 Monfieur

-0.65

lottes

-0.64

ftagPool

-0.64

DoubleQuotes

-0.64

POSITIVE LOGITS

 sources

0.75

Sources

0.62

 Sources

0.59

sources

0.54

 fuentes

0.52

 SOURCES

0.51

 fontes

0.47

industry

0.47

 Quellen

0.47

 industry

0.46

Activations Density 0.167%

references to sources or insiders providing information

No Comments

No Known Activations