INDEX

Explanations

mentions of the word "space"

oai_token-act-pair · gemini-2.0-flash

space-related terms

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

space

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

CPtr

-0.48

lm

-0.44

 terang

-0.43

 Land

-0.42

idea

-0.40

CompleteListener

-0.40

Space

-0.38

 Space

-0.38

rect

-0.36

 nature

-0.35

POSITIVE LOGITS

ThroughAttribute

0.69

LLocation

0.68

writeFieldEnd

0.67

 MainAxisSize

0.66

WebVitals

0.65

tonsoft

0.65

})();

0.65

 насељу

0.65

AndEndTag

0.63

 חיצוניים

0.61

Activations Density 0.255%

mentions of the word "space"

space-related terms

space

No Comments

No Known Activations