INDEX

Explanations

mentions of various procedures or setups in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 '\\;'

-1.04

 للمعارف

-1.03

WebVitals

-0.98

GIVEREF

-0.97

iotensin

-0.96

HtmlAttribute

-0.96

mybatisplus

-0.95

 سكانية

-0.92

GetBytes

-0.92

JspWriter

-0.92

POSITIVE LOGITS

 procedure

0.98

 procedures

0.95

SETUP

0.94

 SETUP

0.85

 setup

0.83

 Procedure

0.79

 Procedures

0.79

 setups

0.77

Setup

0.74

 procedura

0.74

Activations Density 0.112%

mentions of various procedures or setups in context

No Comments

No Known Activations