INDEX

Explanations

a grab bag of specific patterns in code, French words, and personal ads

oai_token-act-pair · gemini-2.0-flash

words related to specificity or plurality

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

Code or foreign languages

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

writeFieldEnd

-0.81

EndContext

-0.77

oredCriteria

-0.76

IUrlHelper

-0.69

StructEnd

-0.68

SharedDtor

-0.67

 ciasc

-0.67

SequentialGroup

-0.67

DeleteBehavior

-0.66

DebuggerNonUser

-0.66

POSITIVE LOGITS

 those

0.94

Those

0.81

those

0.80

 Those

0.79

mga

0.74

那些

0.74

 ones

0.73

 những

0.67

 THOSE

0.60

ские

0.60

Activations Density 0.826%

a grab bag of specific patterns in code, French words, and personal ads

words related to specificity or plurality

Code or foreign languages

No Comments

No Known Activations