INDEX

Explanations

programming-related keywords and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 necessidades

-0.47

Zie

-0.47

 Bors

-0.46

DockStyle

-0.46

(),

-0.45

든

-0.44

component

-0.44

 niezbęd

-0.43

POSITIVE LOGITS

 rowspan

6.00

multirow

1.93

 <<<<<<<<<<<<<<

1.01

enumi

0.99

 GenerationType

0.86

CloseOperation

0.85

 defaultstate

0.83

tagHelperRunner

0.82

 onOptions

0.80

 CreateTagHelper

0.80

Activations Density 0.020%

programming-related keywords and syntax

No Comments

No Known Activations