INDEX

Explanations

code syntax and structure, particularly focusing on method definitions and their parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

ſelves

-1.17

 purpoſe

-1.15

 myſelf

-1.08

 houſe

-1.08

 ſche

-1.07

 raiſ

-1.06

 pleaſure

-1.06

 ſtate

-1.04

 uſed

-1.04

 Theſe

-1.04

POSITIVE LOGITS

0.98

and

0.96

or

0.84

0.75

in

0.74

as

0.64

of

0.63

is

0.62

Activations Density 0.811%

code syntax and structure, particularly focusing on method definitions and their parameters

No Comments

No Known Activations