INDEX

Explanations

text related to technical or coding terminology, particularly 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 @ 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

 للاسماء

-0.94

TintMode

-0.90

 Majefty

-0.89

GeoNames

-0.88

ientras

-0.85

 kaarangay

-0.85

 Monfieur

-0.81

 Meksiku

-0.79

 religieuses

-0.78

 ویکی‌پدی

-0.77

POSITIVE LOGITS

<bos>

0.59

0.58

0.56

0.55

0.54

un

0.54

Activations Density 1.684%

text related to technical or coding terminology, particularly in programming contexts

No Comments

No Known Activations