INDEX

Explanations

questions and directives about actions to take

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 *)__

-0.72

enderror

-0.71

bå

-0.66

 müh

-0.63

 doublet

-0.61

 picker

-0.61

 BrowserModule

-0.61

 ComVisible

-0.61

Picked

-0.60

).__

-0.60

POSITIVE LOGITS

 initComponents

0.75

MessageTagHelper

0.71

 getItemId

0.65

to

0.64

 inside

0.64

 outside

0.62

سطس

0.60

OrWhiteSpace

0.60

fgaben

0.60

bulin

0.58

Activations Density 0.106%

questions and directives about actions to take

No Comments

No Known Activations