INDEX

Explanations

references to specific genes, proteins, or biological entities, particularly in the context of clinical research and studies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SharedCtor

-0.77

Архівовано

-0.60

kaŭ

-0.58

Filmographie

-0.57

PhysRev

-0.57

 Karn

-0.56

 internetowa

-0.56

 بيها

-0.56

*}[

-0.55

OrWhiteSpace

-0.55

POSITIVE LOGITS

Cl

1.53

CL

1.43

Cl

1.40

cl

1.40

cl

1.38

CL

1.34

Cla

1.33

Cla

1.15

Cli

1.14

Kl

1.09

Activations Density 2.609%

references to specific genes, proteins, or biological entities, particularly in the context of clinical research and studies

No Comments

No Known Activations