INDEX

Explanations

references to documents and documentation concepts

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

enumii

-0.66

ArgsConstructor

-0.53

 tkinter

-0.52

sizeCache

-0.48

Jal

-0.45

 pygame

-0.45

 Bened

-0.45

 المعيارى

-0.45

 disambiguazione

-0.44

Captor

-0.44

POSITIVE LOGITS

umente

0.76

umen

0.71

umented

0.65

umenti

0.64

umentos

0.63

UMENTS

0.62

ations

0.62

um

0.60

umenta

0.59

umet

0.59

Activations Density 0.168%

references to documents and documentation concepts

No Comments

No Known Activations