INDEX

Explanations

terms related to academic discourse and technical language in a research context

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

UserScript

-0.71

 Wikimedijinoj

-0.69

 relâche

-0.66

GIH

-0.66

ThroughAttribute

-0.64

IsPostBack

-0.63

LabelTagHelper

-0.63

KommentareTeilen

-0.60

IUrlHelper

-0.58

culoskeletal

-0.58

POSITIVE LOGITS

TagMode

0.77

 interrupted

0.61

 suspending

0.58

 suspend

0.58

 cultivation

0.56

 suspen

0.55

lice

0.54

 distracted

0.54

 suspended

0.53

 arada

0.52

Activations Density 2.527%

terms related to academic discourse and technical language in a research context

No Comments

No Known Activations