INDEX

Explanations

programming constructs and structures related to data handling and output formatting

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

mybatisplus

-1.28

 '\\;'

-1.06

EDEFAULT

-1.01

 pinulongan

-0.99

verwijspagina

-0.93

InjectAttribute

-0.91

 محفوظة

-0.91

 виправивши

-0.90

 Administrativna

-0.89

CloseOperation

-0.88

POSITIVE LOGITS

[_

0.50

let

0.48

 discu

0.46

arius

0.44

return

0.43

 trist

0.42

oree

0.42

 interna

0.42

ency

0.41

Activations Density 0.598%

programming constructs and structures related to data handling and output formatting

No Comments

No Known Activations