INDEX

Explanations

text related to measurement or evaluation methods, particularly in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

IntoConstraints

-0.73

 consultato

-0.67

parsedMessage

-0.65

 препратки

-0.62

xaml

-0.60

mybatisplus

-0.60

 viewDidLoad

-0.59

posedge

-0.56

ähle

-0.55

MigrationBuilder

-0.54

POSITIVE LOGITS

bing

0.71

berly

0.70

bers

0.68

 AssemblyTitle

0.67

berley

0.66

bed

0.65

bin

0.63

bles

0.63

berman

0.59

bs

0.58

Activations Density 0.177%

text related to measurement or evaluation methods, particularly in scientific contexts

No Comments

No Known Activations