INDEX

Explanations

references to users and clients in relation to service documentation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.83

GenerationType

-0.80

 PyTuple

-0.67

统

-0.60

 vanskelig

-0.58

 coordinating

-0.57

brin

-0.56

IVEREF

-0.55

DebuggerStep

-0.54

 ModelExpression

-0.53

POSITIVE LOGITS

 customers

0.98

 clients

0.94

 clientèle

0.92

 readers

0.90

 viewers

0.84

 subscribers

0.83

 users

0.82

 clientes

0.81

 Customers

0.81

 patrons

0.80

Activations Density 0.337%

references to users and clients in relation to service documentation

No Comments

No Known Activations