INDEX

Explanations

references to medical and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 typelib

-0.69

(!__

-0.58

Fordítás

-0.57

 Walkover

-0.56

Искәрмәләр

-0.56

 Económica

-0.56

 ExecuteAsync

-0.54

 Boswell

-0.53

Germ

-0.52

Jeografia

-0.51

POSITIVE LOGITS

 pinulongan

0.72

RenderAtEndOf

0.57

BagConstraints

0.55

Rcpp

0.54

}{*}{}

0.53

CppCodeGen

0.50

!*\

0.50

Het

0.49

RegressionTest

0.49

 nødven

0.49

Activations Density 0.778%

references to medical and legal terminology

No Comments

No Known Activations