INDEX

Explanations

keyword declarations in code contexts

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

<start_of_turn>user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

:✨

-0.54

Hozzáférés

-0.51

TagMode

-0.50

AddTagHelper

-0.49

esterno

-0.46

PreferredItem

-0.45

retudo

-0.45

 vocês

-0.45

 novamente

-0.45

تقاوى

-0.45

POSITIVE LOGITS

IContainer

0.52

SerializeField

0.51

 bist

0.47

 microm

0.46

 Centre

0.46

 intersecting

0.45

Vag

0.45

astéro

0.44

 handling

0.44

Ty

0.43

Activations Density 0.002%

keyword declarations in code contexts

<start_of_turn>user

No Comments

No Known Activations