INDEX

Explanations

states of being already, and words pertaining to oxygen and opportunity.

oai_token-act-pair · gemini-2.0-flash

words related to "taken" or "occupied"

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

Taken/occupied

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

Personensuche

-0.84

########.

-0.80

EndGlobalSection

-0.76

SharedDtor

-0.75

UnknownFieldSet

-0.72

tagHelperRunner

-0.72

MemoryWarning

-0.72

 كومونز

-0.72

ніципалі

-0.71

RTEE

-0.71

POSITIVE LOGITS

 taken

1.64

taken

1.46

Taken

1.38

 Taken

1.36

 TAKEN

1.16

 occupied

1.05

 spoken

1.03

 take

0.80

occupied

0.73

Take

0.73

Activations Density 1.724%

states of being already, and words pertaining to oxygen and opportunity.

words related to "taken" or "occupied"

Taken/occupied

No Comments

No Known Activations