INDEX

Explanations

names of individuals and their associated attributes or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

+#+#

-1.02

expandindo

-0.87

principalTable

-0.87

 ExecuteAsync

-0.85

LookAnd

-0.83

AddTagHelper

-0.81

+#+

-0.81

WithIOException

-0.79

SizeF

-0.79

 lenker

-0.77

POSITIVE LOGITS

 today

0.50

SNAPSHOT

0.48

apiVersion

0.47

ambiguation

0.46

ูป

0.45

Deactivate

0.44

 living

0.44

 bologna

0.43

 obrazu

0.42

 becoming

0.42

Activations Density 0.243%

names of individuals and their associated attributes or actions

No Comments

No Known Activations