INDEX

Explanations

concepts related to groups, comparisons, and various forms of evidence in legal or research contexts

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

elements related to evidence, details of cases, or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

例句

-0.51

 nawr

-0.49

UnusedPrivate

-0.46

Dichloropropane

-0.45

 igjen

-0.44

EndContext

-0.44

 Fully

-0.44

 censiti

-0.43

 noten

-0.43

 Everybody

-0.43

POSITIVE LOGITS

|}{$

0.63

DebuggerNonUser

0.56

NgModule

0.54

politan

0.54

ändler

0.54

GoogleMap

0.53

ChildIndex

0.53

istica

0.53

 encomp

0.53

 Italijanski

0.53

Activations Density 1.561%

concepts related to groups, comparisons, and various forms of evidence in legal or research contexts

elements related to evidence, details of cases, or studies

No Comments

No Known Activations