INDEX

Explanations

assertions of correctness or truthfulness in arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ArrowToggle

-0.67

QMetaType

-0.61

StoreMessageInfo

-0.61

 дописавши

-0.60

 Roskov

-0.60

aarrggbb

-0.60

 SqlDbType

-0.60

verwijspagina

-0.58

 архивлан

-0.57

PyExc

-0.57

POSITIVE LOGITS

 true

0.65

没错

0.64

 vrai

0.64

 truth

0.62

 agreed

0.59

true

0.59

Indeed

0.58

 agree

0.58

ReusableCell

0.58

 valid

0.58

Activations Density 0.514%

assertions of correctness or truthfulness in arguments

No Comments

No Known Activations