INDEX

Explanations

questions that seek clarification or provoke thought

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 Bradley

-0.81

Bradley

-0.81

*/].

-0.74

 Jefus

-0.72

 sumpay

-0.71

 Saif

-0.71

 Chriſt

-0.71

 Grun

-0.70

𝓫

-0.69

wiście

-0.69

POSITIVE LOGITS

Datuak

0.75

 EconPapers

0.70

zydent

0.69

 Eilish

0.68

0.67

ագրություններ

0.65

chiali

0.64

 concha

0.64

AutoField

0.62

 Gleaner

0.62

Activations Density 0.123%

questions that seek clarification or provoke thought

No Comments

No Known Activations