INDEX

Explanations

function declarations related to creating, returning, or manipulating objects within a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

-0.56

<eos>

-0.56

-0.55

-0.54

-0.53

“

-0.51

--

-0.50

-0.49

POSITIVE LOGITS

 Monfieur

1.07

 itſelf

1.06

 myſelf

1.05

ſelf

1.04

 Majefty

1.01

ſelves

0.97

 Houſe

0.96

 ―――――

0.96

 Cæsar

0.96

 Shakspeare

0.95

Activations Density 0.445%

function declarations related to creating, returning, or manipulating objects within a programming context

No Comments

No Known Activations