INDEX

Explanations

terms related to biological and computational concepts, particularly in the context of immune responses and molecular details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

GEBURTSDATUM

-0.82

BibitemShut

-0.80

\<^

-0.70

AddHtmlAttribute

-0.68

 TextAppearance

-0.68

CloseOperation

-0.65

 Erişim

-0.64

istically

-0.64

<",

-0.64

RectangleBorder

-0.63

POSITIVE LOGITS

0.49

 právě

0.45

ou

0.45

kozások

0.44

 kır

0.43

 thăng

0.43

 vettor

0.43

ars

0.42

fuhr

0.42

Activations Density 0.488%

terms related to biological and computational concepts, particularly in the context of immune responses and molecular details

No Comments

No Known Activations