INDEX

Explanations

terms related to programming and software constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

发表于

-0.43

Especificación

-0.42

 ſta

-0.40

 EINVAL

-0.39

 assistants

-0.39

 gouttes

-0.38

 inalámb

-0.36

cuela

-0.36

 infection

-0.36

 Reised

-0.36

POSITIVE LOGITS

EndContext

0.63

rungsseite

0.63

ⓧ

0.62

typeorm

0.58

 concrete

0.58

 للاسماء

0.58

concrete

0.57

 Condu

0.56

 Reverso

0.54

TagMode

0.53

Activations Density 1.943%

terms related to programming and software constructs

No Comments

No Known Activations