INDEX

Explanations

data and structural identifiers or codes used in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

JAXB

-0.60

skj

-0.53

AutoScale

-0.52

protoimpl

-0.50

ThroughAttribute

-0.49

 AssemblyProduct

-0.49

LEncoder

-0.48

insics

-0.48

sprogramm

-0.47

ジュール

-0.47

POSITIVE LOGITS

 Castelo

0.49

ivamente

0.48

тация

0.46

 Saxons

0.46

 tỉ

0.46

Ruh

0.46

⑨

0.45

henswürdigkeiten

0.45

 ujednoznacz

0.45

جغرافيا

0.45

Activations Density 0.380%

data and structural identifiers or codes used in scientific or technical contexts

No Comments

No Known Activations