INDEX

Explanations

instances/words related to reporting, coding, and sports fighting

oai_token-act-pair · gemini-2.0-flash

technical terms in programming or API references

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

Code snippets

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

ohyd

-0.53

×

-0.51

×

-0.51

ثيق

-0.47

TintMode

-0.47

Przypisy

-0.46

omás

-0.45

times

-0.45

 times

-0.44

endimiento

-0.44

POSITIVE LOGITS

//

0.71

 Audiodateien

0.71

 MainAxisSize

0.71

хьтан

0.64

Raw

0.63

])):

0.62

 SDLK

0.62

RAW

0.61

}{*}{}

0.60

jspb

0.60

Activations Density 0.288%

instances/words related to reporting, coding, and sports fighting

technical terms in programming or API references

Code snippets

No Comments

No Known Activations