INDEX

Explanations

terms related to programming and medical manifestations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ugier

-0.74

ionario

-0.67

 démission

-0.67

 ModelExpression

-0.64

 passés

-0.64

zyści

-0.63

 fermés

-0.62

Bisous

-0.61

الدراسه

-0.61

aderie

-0.61

POSITIVE LOGITS

 spirit

0.67

 Spirit

0.63

 consciousness

0.61

esprit

0.58

rend

0.57

gau

0.56

Spirit

0.56

 surla

0.56

layoutControl

0.56

Mind

0.56

Activations Density 3.161%

terms related to programming and medical manifestations

No Comments

No Known Activations