INDEX

Explanations

scientific terminology and acronyms related to research methodologies and analysis methods

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

ური

-0.75

Datuak

-0.70

 disponibilités

-0.69

Hozzáférés

-0.69

+'.

-0.65

комму

-0.64

ichord

-0.63

CppMethod

-0.62

+</

-0.61

Identyfik

-0.61

POSITIVE LOGITS

 Rovers

0.91

 BorderRadius

0.89

 Rask

0.85

 Rahim

0.85

RSD

0.84

PhysRev

0.83

Ruk

0.82

 RequestMethod

0.82

RDC

0.81

Activations Density 1.937%

scientific terminology and acronyms related to research methodologies and analysis methods

No Comments

No Known Activations