INDEX

Explanations

references to utility functions or classes in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ThroughAttribute

-0.78

oglobulin

-0.75

 bParam

-0.74

ony

-0.70

|>

-0.70

 IndexPath

-0.64

İstinadlar

-0.64

Décès

-0.64

MethodManager

-0.64

POSITIVE LOGITS

Utils

1.68

Util

1.62

 Utils

1.13

 Util

0.95

 ſte

0.72

CollectionUtils

0.69

Config

0.68

Helper

0.64

IOUtils

0.61

 ſch

0.60

Activations Density 0.085%

references to utility functions or classes in programming

No Comments

No Known Activations

references to utility functions or classes in programming

No Comments

No Known Activations