INDEX

Explanations

occurrences of the term "familiarity" and related concepts describing familiarity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"familiar"

np_acts-logits-general · gemini-2.0-flash

familiarity

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.61

SequentialGroup

-0.61

aarrggbb

-0.60

hyrchwyd

-0.56

WithIOException

-0.54

GEBURTSDATUM

-0.54

 ModelExpression

-0.52

 otomatig

-0.51

 AspNetCore

-0.50

 nakalista

-0.50

POSITIVE LOGITS

 familiar

3.02

familiar

2.64

 familiarity

2.50

Familiar

2.48

 Familiar

2.48

 familiarize

2.03

熟悉

1.98

famili

1.95

Famili

1.88

 famili

1.85

Activations Density 0.145%

occurrences of the term "familiarity" and related concepts describing familiarity

"familiar"

familiarity

No Comments

No Known Activations