INDEX

Explanations

references to specific scientific concepts and their associated terminologies, especially in the context of biological or computational research

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

(!__

-0.83



-0.76

GIVEREF

-0.74

MIDDLEWARE

-0.73

évaluateur

-0.73

EDEFAULT

-0.72

WSGI

-0.68

IANGLES

-0.67

CORBA

-0.67

 onOptions

-0.67

POSITIVE LOGITS

 Pals

1.03

 getP

0.92

Pn

0.92

 Pirates

0.87

PSS

0.86

 Pind

0.85

0.83

PPA

0.82

Pá

0.79

PTS

0.79

Activations Density 2.194%

references to specific scientific concepts and their associated terminologies, especially in the context of biological or computational research

No Comments

No Known Activations