INDEX

Explanations

terms related to interpersonal dynamics and mental well-being, detecting the theme of psychology

oai_token-act-pair · gemini-2.0-flash

patterns

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

 tombé

-0.59

 ennemi

-0.55

 vectorielles

-0.54

humble

-0.52

 vectorielle

-0.52

 mélanger

-0.52

Autoritní

-0.50

MUX

-0.50

يميديا

-0.50

exposure

-0.50

POSITIVE LOGITS

ThroughAttribute

0.73

 насељу

0.66

MENAFN

0.63

EDEFAULT

0.60

 ModelExpression

0.58

ReusableCell

0.57

 незавершена

0.57

TypedDataSet

0.54

JspWriter

0.53

})*/

0.53

Activations Density 0.806%

terms related to interpersonal dynamics and mental well-being, detecting the theme of psychology

patterns

No Comments

No Known Activations