INDEX

Explanations

names of people, places, or groups related to various 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

ometrics

-0.57

etz

-0.56

ak

-0.56

llac

-0.56

ay

-0.55

ogenic

-0.55

jų

-0.54

otype

-0.54

hra

-0.54

ura

-0.54

POSITIVE LOGITS

ędziesz

0.46

EndProject

0.44

sizeCache

0.44

RegressionTest

0.43

ącz

0.42

InjectAttribute

0.42

 typelib

0.42

angkut

0.41

umpulkan

0.41

 виправивши

0.41

Activations Density 1.638%

names of people, places, or groups related to various contexts

No Comments

No Known Activations