INDEX

Explanations

information about films, particularly when it involves a description of the film or its production

oai_token-act-pair · gemini-2.0-flash

words related to films and their details

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

Media descriptions

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

KommentareTeilen

-0.82

:✨

-0.68

Datuak

-0.66

 doInBackground

-0.65

bootstrapcdn

-0.65

.*")]

-0.59

httphttps

-0.59

mybatisplus

-0.57

]--;

-0.57

Hochspringen

-0.57

POSITIVE LOGITS

 starred

0.57

 drew

0.55

 estrela

0.54

 stars

0.52

 became

0.52

 star

0.49

InitStructure

0.47

stva

0.47

 discut

0.46

sat

0.46

Activations Density 1.149%

information about films, particularly when it involves a description of the film or its production

words related to films and their details

Media descriptions

No Comments

No Known Activations