INDEX

Explanations

references to modes 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

addContainerGap

-0.82

expandindo

-0.64

WriteBarrier

-0.64

 mapStateToProps

-0.63

Referencie

-0.62

signable

-0.61

 jeter

-0.58

Spill

-0.58

rollup

-0.58

UnsafeEnabled

-0.58

POSITIVE LOGITS

 Modes

1.34

modes

1.32

 modes

1.32

 Mode

1.30

Modes

1.30

 MODE

1.25

 mode

1.18

mode

1.17

Mode

1.10

setMode

1.07

Activations Density 0.056%

references to modes or states

No Comments

No Known Activations