INDEX

Explanations

references to "dam" and "dams" in the text

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

Dampeer, damsel, dams

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

 pica

-0.54

keit

-0.53

antik

-0.49

Quint

-0.49

kle

-0.48

ftime

-0.47

hite

-0.47

 Sonny

-0.47

LIV

-0.47

 Voit

-0.47

POSITIVE LOGITS

dam

2.06

 dams

1.99

Dam

1.82

Dam

1.67

 Dams

1.59

dam

1.46

DAM

1.38

dams

1.30

DAM

1.09

 Damas

0.90

Activations Density 0.002%

references to "dam" and "dams" in the text

Dampeer, damsel, dams

No Comments

No Known Activations