INDEX

Explanations

terms related to confirmation and verification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ftagPool

-0.90

AutoScale

-0.62

naux

-0.59

RuleContext

-0.56

primaryStage

-0.56

ATURA

-0.54

 Inch

-0.54

 widest

-0.54

 AspNetCore

-0.54

 <<<<<<<<<<<<<<

-0.54

POSITIVE LOGITS

</thead>

0.53

ImageContext

0.49

opress

0.48

transQ

0.48

HasBeenSet

0.47

 Chwiliwch

0.47

Portail

0.47

 Pauly

0.47

//-->

0.46

usercontent

0.46

Activations Density 0.069%

terms related to confirmation and verification processes

No Comments

No Known Activations