INDEX

Explanations

phrases and numbers related to data and analysis

oai_token-act-pair · gemini-2.0-flash

words or terms that signify identification or categorization

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

say "hyphen"

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

-0.82

-0.71

-0.69

-0.59

</

-0.56

UnusedPrivate

-0.54

</em>

-0.50

</strong>

-0.50

POSITIVE LOGITS

featureID

0.86

цездатний

0.81

 doInBackground

0.75

 bezeichneter

0.75

 VizieR

0.75

 Мексичка

0.70

Efq

0.70

 Shakspeare

0.69

parsedMessage

0.69

 الدولى

0.69

Activations Density 7.725%

phrases and numbers related to data and analysis

words or terms that signify identification or categorization

say "hyphen"

No Comments

No Known Activations