INDEX

Explanations

references to accountability or responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

évaluateur

-0.81

WriteBarrier

-0.68

RemoveField

-0.67

+#+

-0.66

BibitemShut

-0.66

EROUS

-0.65

 wikipagina

-0.64

ethene

-0.63

nables

-0.63

OptionsMenu

-0.62

POSITIVE LOGITS

 account

0.88

 quote

0.83

Client

0.82

 quoted

0.78

om

0.78

 client

0.76

 Client

0.76

fix

0.72

 Account

0.72

client

0.71

Activations Density 0.146%

references to accountability or responsibility

No Comments

No Known Activations