INDEX

Explanations

function-related testing assertions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Charlene

-0.76

HHHHHHHH

-0.72

 araw

-0.69

erle

-0.66

ToDecimal

-0.66

 Brenner

-0.65

bobox

-0.65

OMEM

-0.64

écnicas

-0.64

DeleteBehavior

-0.64

POSITIVE LOGITS

it

2.56

IT

1.84

It

1.49

IT

1.45

it

1.44

It

1.25

its

1.20

它

1.04

itm

1.00

itl

0.98

Activations Density 0.052%

function-related testing assertions

No Comments

No Known Activations