INDEX

Explanations

terms related to actions and functions in programming contexts

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

$_"

-0.75

ENODEV

-0.69

IsPostBack

-0.67

 Monfieur

-0.66

duate

-0.66

 orderBy

-0.65

 OMITBAD

-0.64

neſs

-0.64

 themſelves

-0.64

 Exactos

-0.63

POSITIVE LOGITS

Action

1.52

action

1.39

ACTION

1.34

 Action

1.20

actions

1.14

Actions

1.05

getAction

1.03

addAction

1.01

 ACTION

0.99

setAction

0.95

Activations Density 0.099%

terms related to actions and functions in programming contexts

No Comments

No Known Activations