INDEX

Explanations

words or phrases that identify locations in time, either specific times or relative times

oai_token-act-pair · gemini-2.0-flash

terms related to game periods or time frames

np_token-act-pair-logits · gpt-4o-mini

time segments

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.72

::::::::

-0.57

RenderAtEndOf

-0.52

 preocupes

-0.47

://$

-0.47

 Sloane

-0.44

awaiter

-0.44

TypedDataSet

-0.44

Square

-0.43

apimachinery

-0.43

POSITIVE LOGITS

MemoryWarning

0.66

 period

0.63

AccessorTable

0.63

VersionUID

0.62

 Period

0.62

Fordítás

0.58

 makeStyles

0.56

featureID

0.56

period

0.56

 AttributeSet

0.55

Activations Density 0.505%

words or phrases that identify locations in time, either specific times or relative times

terms related to game periods or time frames

time segments

No Comments

No Known Activations