INDEX

Explanations

commands and references related to command line usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ViewInit

-0.61

။

-0.60

<!--[

-0.60



-0.59

abestanden

-0.59

اطر

-0.58

 Lagi

-0.58

 isos

-0.57

}")

-0.57

 relu

-0.57

POSITIVE LOGITS

 command

3.06

 Command

3.03

Command

2.87

command

2.86

 COMMAND

2.74

 commands

2.74

 Commands

2.55

COMMAND

2.53

commands

2.49

 commanded

2.23

Activations Density 0.046%

commands and references related to command line usage

No Comments

No Known Activations