INDEX

Explanations

general, high-frequency words such as articles, prepositions, and some adjectives and adverbs, often appearing together in common phrases.

oai_token-act-pair · gemini-2.0-flash

a

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

las

-0.50

la

-0.36

ıldığı

-0.36

✫

-0.35

__

-0.35

::

-0.35

riezmann

-0.34

-0.33

ia

-0.33

POSITIVE LOGITS

ModelAdmin

0.83

ousand

0.82

tvguidetime

0.81

 Houſe

0.81

 Theſe

0.80

principalColumn

0.76

 tranf

0.75

ousands

0.75

 Diſ

0.74

CloseOperation

0.74

Activations Density 7.355%

general, high-frequency words such as articles, prepositions, and some adjectives and adverbs, often appearing together in common phrases.

a

No Comments

No Known Activations