INDEX

Explanations

The neuron focuses on the word "document" and words related to recent events or locations like "date", "index", "recent" and "inner" when "document" is not present.

oai_token-act-pair · gemini-2.0-flash

document

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

nasium

-0.66

()")

-0.66

'")

-0.62

."],

-0.61

songwriter

-0.57

%"),

-0.57

NSYLVANIA

-0.57

etheless

-0.56

;';

-0.56

hauled

-0.55

POSITIVE LOGITS

GEBURTSDATUM

1.28

ThroughAttribute

1.22

 <<<<<<<<<<<<<<

1.16

 nakalista

1.12

+#+#

1.08

 nahilalakip

1.04

 surla

1.03

Revenir

1.01

providedIn

0.97

 resourceCulture

0.94

Activations Density 1.782%

The neuron focuses on the word "document" and words related to recent events or locations like "date", "index", "recent" and "inner" when "document" is not present.

document

No Comments

No Known Activations