INDEX

Explanations

terms related to legal standards and evidentiary requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AnimationsModule

-0.52

SequentialGroup

-0.46

 ProtoMessage

-0.41

 Mond

-0.39

 Kaiser

-0.38

zension

-0.37

Bioaccumulative

-0.36

 plan

-0.36

entend

-0.36

hook

-0.35

POSITIVE LOGITS

 uncertainty

0.85

 uncertainties

0.79

uncertainty

0.76

 Uncertainty

0.71

 uncertain

0.68

Uncertainty

0.68

 incertidumbre

0.67

 Uncertain

0.65

 scepticism

0.63

 certainty

0.62

Activations Density 1.758%

terms related to legal standards and evidentiary requirements

No Comments

No Known Activations