INDEX

Explanations

function and return statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 disambiguazione

-0.98

IsMutable

-0.90

Personendaten

-0.85

protoimpl

-0.84

 transfieras

-0.83

 ſte

-0.81

 estekak

-0.80

 indígen

-0.79

fjspx

-0.79

 ſta

-0.77

POSITIVE LOGITS

↵↵

0.48

0.47

↵

0.45

0.42

↵↵↵

0.41

ui

0.38

0.37

ul

0.37

<eos>

0.36

CO

0.36

Activations Density 0.161%

function and return statements in code

No Comments

No Known Activations