INDEX

Explanations

keywords and structures related to programming functions and error handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

]='\

-0.73

 disambiguazione

-0.66

]--;

-0.64

 insuffisamment

-0.63

 متعلقه

-0.63

 ***!

-0.60

spesies

-0.60

PMailer

-0.59

(@"%@",

-0.58

 "-";

-0.57

POSITIVE LOGITS

sprintf

0.99

 sprintf

0.85

Sprintf

0.76

fmt

0.71

Infof

0.66

Printf

0.66

snprintf

0.62

fmt

0.62

0.55

format

0.54

Activations Density 0.252%

keywords and structures related to programming functions and error handling

No Comments

No Known Activations