INDEX

Explanations

terms related to accidental or unintentional occurrences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dentelle

-0.70

 habet

-0.68

 soeur

-0.68

writerow

-0.67

 vendus

-0.64

 rispet

-0.64

 supérieures

-0.64

 fær

-0.63

 neuve

-0.63

 Vierge

-0.63

POSITIVE LOGITS

 incidental

1.04

 casually

0.99

idental

0.93

 casual

0.91

casual

0.88

IDENTAL

0.87

Casual

0.85

 random

0.81

 haphazard

0.81

 incidentally

0.77

Activations Density 0.282%

terms related to accidental or unintentional occurrences

No Comments

No Known Activations