INDEX

Explanations

references to medical or biological parameters and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

<eos>

-0.61

 lumen

-0.52

gdx

-0.48

 scope

-0.46

razioni

-0.43

—

-0.43

鼠

-0.42

heure

-0.42

gas

-0.42

</h1>

-0.41

POSITIVE LOGITS

RuleContext

0.75

RenderAtEndOf

0.74

parsedMessage

0.73

Искәрмәләр

0.72

AddTagHelper

0.70

MigrationBuilder

0.70

SourceChecksum

0.70

GenerationType

0.68

 BrowserModule

0.67

RegressionTest

0.67

Activations Density 0.294%

references to medical or biological parameters and measurements

No Comments

No Known Activations