INDEX

Explanations

references to data 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 @ 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

ⓧ

-0.91

rungsseite

-0.90

RenderAtEndOf

-0.87

TagHelper

-0.83

StructEnd

-0.79

SharedDtor

-0.78

ineno

-0.75

 estimés

-0.74

 بيها

-0.74

 فريبيس

-0.71

POSITIVE LOGITS

 premise

0.40

string

0.38

dig

0.38

asa

0.38

ού

0.36

 user

0.36

dig

0.36

Go

0.36

 data

0.35

imp

0.35

Activations Density 0.791%

references to data and measurements

No Comments

No Known Activations