INDEX

Explanations

instances of blame and excuse-making and also picks up on other argumentation and use of language to affect emotion

oai_token-act-pair · gemini-2.0-flash

avoidance

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

UnusedPrivate

-0.62

WithMany

-0.61

 Interchange

-0.57

styleType

-0.56

richTextPanel

-0.56

featureID

-0.55

 trunks

-0.55

Espèce

-0.51

smithy

-0.51

addCriterion

-0.50

POSITIVE LOGITS

 AssemblyCulture

0.69

 avoidance

0.68

Avoid

0.56

 Avoidance

0.55

SequentialGroup

0.52

 fuir

0.51

 avoiding

0.50

 Avoid

0.50

逃避

0.49

 refuge

0.49

Activations Density 1.675%

instances of blame and excuse-making and also picks up on other argumentation and use of language to affect emotion

avoidance

No Comments

No Known Activations