INDEX

Explanations

scientific terminology related to immune responses and antibody mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AndEndTag

-0.75

المناصب

-0.75

TagMode

-0.71

IntoConstraints

-0.70

AccessorTable

-0.69

Datuak

-0.68

DebuggerNonUser

-0.66

 BoxDecoration

-0.63

Filmo

-0.63

verwijspagina

-0.63

POSITIVE LOGITS

 antibody

1.13

 antibodies

1.12

IgG

0.96

IgG

0.95

 Antibodies

0.91

 Antibody

0.88

Antibodies

0.85

 immunoglobulin

0.82

Antibody

0.81

IgM

0.74

Activations Density 0.967%

scientific terminology related to immune responses and antibody mechanisms

No Comments

No Known Activations