INDEX

Explanations

references to the term "Hind" as well as its variations and context in a text

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

hindlimb, hindgut, hindwings

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

cashire

-0.50

 Kran

-0.49

ToProps

-0.47

rac

-0.44

 Frisch

-0.44

 Breen

-0.44

 Clancy

-0.43

orianCalendar

-0.43

 yourselves

-0.43

 Noma

-0.43

POSITIVE LOGITS

 Hind

1.02

Hind

0.99

hind

0.85

 hind

0.84

 Andres

0.71

 Falk

0.65

wik

0.62

 enfans

0.61

Falk

0.60

Andres

0.59

Activations Density 0.007%

references to the term "Hind" as well as its variations and context in a text

hindlimb, hindgut, hindwings

No Comments

No Known Activations