INDEX

Explanations

references to numerical values and parameters in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Chwiliwch

-0.60

ंदीखरीदारी

-0.56

ModelAdmin

-0.51

IndentedString

-0.51

Демографія

-0.50

Amounts

-0.49

WithIOException

-0.49

protoimpl

-0.48

arounds

-0.48

itinéraire

-0.48

POSITIVE LOGITS

 elements

0.92

 constituent

0.91

 individual

0.85

 cells

0.84

 components

0.83

 pixels

0.82

 nodes

0.79

individual

0.77

 atoms

0.75

 constituents

0.74

Activations Density 1.807%

references to numerical values and parameters in a technical context

No Comments

No Known Activations