INDEX

Explanations

words related to collaborative and organizational activities

oai_token-act-pair · gemini-2.0-flash

new improvements

np_max-act-logits · gemini-2.0-flash

say "prepositions"

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 pleaſure

-0.85

 étoient

-0.82

 purpoſe

-0.77

 faſt

-0.77

'{@

-0.74

 дописавши

-0.74

<bos>

-0.72

 ſtate

-0.71

 auroit

-0.71



-0.71

POSITIVE LOGITS

 localVar

0.62

to

0.61

ⓧ

0.49

 Signalez

0.47

in

0.47

zuf

0.46

PYX

0.45

oule

0.44

ndre

0.44

thâu

0.44

Activations Density 34.116%

words related to collaborative and organizational activities

new improvements

say "prepositions"

No Comments

No Known Activations