INDEX

Explanations

references to increasing or elevating actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

iyle

-0.79

endregion

-0.78

]--;

-0.77

BEA

-0.73

DebuggerNonUser

-0.73

STC

-0.72

 Criterion

-0.72

MDC

-0.71

SSC

-0.71

 Modi

-0.70

POSITIVE LOGITS

up

1.82

Up

1.77

UP

1.74

Up

1.61

up

1.46

UP

1.44

AsUp

1.40

 down

1.24

ups

1.22

Ups

1.20

Activations Density 0.123%

references to increasing or elevating actions or states

No Comments

No Known Activations