INDEX

Explanations

the word "wall" and associated terms like "street" or "murals."

oai_token-act-pair · gemini-2.0-flash

references to "Wall" and its variants

np_token-act-pair-logits · gpt-4o-mini

wall

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ecotoxicity

-0.49

ศาสตร์

-0.48

emb

-0.46

Salad

-0.45

räck

-0.44

″]

-0.43

ivotopis

-0.43

 spilled

-0.42

icans

-0.42

 bombas

-0.41

POSITIVE LOGITS

ViewImports

0.78

ImageContext

0.72

FieldBuilder

0.62

AsUp

0.59

ThroughAttribute

0.58

AxisAlignment

0.56

 يتيمه

0.55

__.__

0.54

Билгалдахарш

0.53

')));

0.53

Activations Density 1.031%

the word "wall" and associated terms like "street" or "murals."

references to "Wall" and its variants

wall

No Comments

No Known Activations

the word "wall" and associated terms like "street" or "murals."

references to "Wall" and its variants

wall

No Comments

No Known Activations