INDEX

Explanations

instances of refusal or non-compliance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

XmlAccessType

-0.84

حياته

-0.75

tigt

-0.70

IBOutlet

-0.67

PathVariable

-0.64

BuildContext

-0.63

thern

-0.63

seca

-0.62

adal

-0.61

fekt

-0.61

POSITIVE LOGITS

 refusé

0.93

 refusal

0.92

Willing

0.89

 Refuse

0.89

 refus

0.89

 Willing

0.86

 refusing

0.83

 препратки

0.83

 refuse

0.83

 unwilling

0.82

Activations Density 0.131%

instances of refusal or non-compliance

No Comments

No Known Activations