INDEX

Explanations

descriptions of settings and environments within a narrative

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

thoughts and feelings

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

الإنجليزية

-0.49

المناصب

-0.49

reportError

-0.49

Rüyada

-0.45

 gezegd

-0.44

}{@

-0.44

 explicado

-0.43

 conmigo

-0.40

CROSSTALK

-0.40

 manifestly

-0.40

POSITIVE LOGITS

 thoughts

0.54

 thinking

0.54

 hoping

0.52

 loneliness

0.51

thinking

0.50

 feeling

0.50

 remembering

0.50

 reflection

0.50

 الحره

0.49

Thinking

0.48

Activations Density 0.056%

descriptions of settings and environments within a narrative

thoughts and feelings

No Comments

No Known Activations