INDEX

Explanations

elements related to data structures or statistics, including formatted entries, possibly in a table or list format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

syms

-0.45

WithIOException

-0.44

-0.39

CDCl

-0.39

Begriffsklä

-0.39

tetrahydro

-0.37

Substring

-0.37

organ

-0.37

visel

-0.37

CharStream

-0.37

POSITIVE LOGITS

NewUrlParser

0.98

Personendaten

0.88

0.85

 Baillargeon

0.81

省市镇

0.80

 '\\;'

0.77

 acceptez

0.72

AxisAlignment

0.71

 مشين

0.71

 onPostExecute

0.71

Activations Density 0.701%

elements related to data structures or statistics, including formatted entries, possibly in a table or list format

No Comments

No Known Activations