INDEX

Explanations

references to anti-establishment or anti-authority sentiments

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

ScopeManager

-0.85

 snippetHide

-0.68

 UserModel

-0.67

 لينك

-0.66

URLException

-0.66

 queſta

-0.66

 '\\;'

-0.65

 ReSharper

-0.64

ActionMode

-0.63

featureID

-0.62

POSITIVE LOGITS

 pseudo

0.64

 Pseudo

0.59

 multi

0.58

 quasi

0.56

Pseudo

0.55

 Multi

0.54

 auto

0.54

neo

0.54

 self

0.54

Activations Density 1.588%

references to anti-establishment or anti-authority sentiments

No Comments

No Known Activations