INDEX

Explanations

arxiv and PhysRev citations, field theory and numbers with exponents

oai_token-act-pair · gemini-2.0-flash

technical terms and data structure references

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

Code and unusual words

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AccessorTable

-0.61

apimachinery

-0.52

 nhau

-0.52

bitol

-0.51

 access

-0.51

Na

-0.50

access

-0.49

GeneratedMessage

-0.49

 mergeFrom

-0.47

 Access

-0.47

POSITIVE LOGITS

styleUrls

0.69

 linkovi

0.59

UrlEncoded

0.59

NUMX

0.58

 getItemId

0.57

 Offisielt

0.57

WriteBarrier

0.57

AnimationFrame

0.54

Skocz

0.53

tvguidetime

0.53

Activations Density 5.892%

arxiv and PhysRev citations, field theory and numbers with exponents

technical terms and data structure references

Code and unusual words

No Comments

No Known Activations