INDEX

Explanations

content related to profiles or profiling, particularly in a healthcare or data context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 bền

-0.71

IgA

-0.57

nestjs

-0.57

reactstrap

-0.57

 tóxic

-0.55

elasticsearch

-0.55

 يتيمه

-0.54

"]();

-0.53

=$((

-0.53

ylus

-0.53

POSITIVE LOGITS

 profile

5.03

 Profile

4.54

 profiles

4.47

profile

4.31

Profile

4.11

 PROFILE

4.07

 Profiles

3.90

PROFILE

3.65

profiles

3.46

 profil

3.40

Activations Density 0.066%

content related to profiles or profiling, particularly in a healthcare or data context

No Comments

No Known Activations