INDEX

Explanations

references to programming languages and software licenses

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

 MediatR

-0.64

niająca

-0.64

 cref

-0.61

****************

-0.60

BuilderFactory

-0.59

fillStyle

-0.59

Dmitry

-0.58

 ***!

-0.58

**************

-0.56

RepeatedField

-0.56

POSITIVE LOGITS

 Olsen

1.06

Osi

0.97

Oku

0.94

Osw

0.94

 Oats

0.92

 Oates

0.92

ODS

0.91

 Olsson

0.91

Ode

0.91

Ols

0.90

Activations Density 0.590%

references to programming languages and software licenses

No Comments

No Known Activations