INDEX

Explanations

descriptions of objects, buildings, statues, and people in a historical context

oai_token-act-pair · gemini-2.0-flash

stories and myths

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RTDA

-0.51

 canadienne

-0.47

⟬

-0.46

iembre

-0.45

agot

-0.45

IDAD

-0.45

ưỡi

-0.45

AsUp

-0.43

قایناقلار

-0.43

Diwedd

-0.43

POSITIVE LOGITS

BeginContext

0.75

localctx

0.71

modelBuilder

0.66

jspb

0.66

----</

0.65

WireFormatLite

0.64

addCriterion

0.64

 AssemblyProduct

0.63

DebuggerNonUser

0.59

GOTREF

0.59

Activations Density 4.643%

descriptions of objects, buildings, statues, and people in a historical context

stories and myths

No Comments

No Known Activations