INDEX

Explanations

phrases that indicate the presence of key prepositions or articles within a context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ulipas

-0.81

:✨

-0.81

Autoritní

-0.74

cshtml

-0.73

 bezeichneter

-0.73

AddTagHelper

-0.72

 виправивши

-0.71

estus

-0.69

ItemBackground

-0.66

ölkerung

-0.63

POSITIVE LOGITS

Efq

0.88

 Anfitrión

0.75

 raiſ

0.71

 Monfieur

0.68

 Cæsar

0.68

 fuper

0.68

 ſche

0.67

 Reſ

0.67

 ſur

0.67

 purpoſe

0.66

Activations Density 0.219%

phrases that indicate the presence of key prepositions or articles within a context

No Comments

No Known Activations