INDEX

Explanations

terms related to crime scene investigations and evidence collection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

<bos>

-0.65

ServiceImpl

-0.61

__':

-0.57

UpdateCommand

-0.53

dangerous

-0.51

grained

-0.51

 متعلقه

-0.50

 <<<<<<<<<<<<<<

-0.50

idescreen

-0.49

paikan

-0.49

POSITIVE LOGITS

 mysteriously

0.67

TacToe

0.57

 mysterious

0.57

Mysterious

0.55

 mystery

0.55

 Mysterious

0.54

MigrationBuilder

0.54

 unexplained

0.52

 mysteries

0.52

 misterio

0.52

Activations Density 0.497%

terms related to crime scene investigations and evidence collection

No Comments

No Known Activations