INDEX

Explanations

numerical references or labels related to figures and tables in academic or scientific documents

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 myſelf

-0.95

 ―――――

-0.89

IVEREF

-0.88

RegressionTest

-0.86

ſelves

-0.84

 ARXIV

-0.83

حياتها

-0.83

 doubtnut

-0.82

 SIMBAD

-0.82

."</

-0.82

POSITIVE LOGITS

<eos>

0.68

Fm

0.47

0.46

fh

0.45

fá

0.44

ran

0.43

fu

0.42

for

0.41

Activations Density 0.391%

numerical references or labels related to figures and tables in academic or scientific documents

No Comments

No Known Activations