INDEX

Explanations

terms related to medical conditions and health impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 مواليد

-0.70

 HasFactory

-0.64

RegistryLite

-0.56

LabelTagHelper

-0.53

kozások

-0.52

 Ause

-0.50

Jegyzetek

-0.49

WebServlet

-0.49

ArrowToggle

-0.48

crombie

-0.48

POSITIVE LOGITS

 minimal

0.71

 impeccable

0.69

nil

0.66

 limited

0.63

 dieselben

0.60

 intact

0.59

VersionUID

0.58

 endless

0.57

 extensive

0.57

 stimmen

0.57

Activations Density 0.667%

terms related to medical conditions and health impacts

No Comments

No Known Activations