INDEX

Explanations

references to strings in code snippets or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ly

-0.70

 IDisposable

-0.69

kun

-0.69

yü

-0.68

retudo

-0.68

<h3>

-0.68

 leaſt

-0.67

 Emery

-0.66

peč

-0.66

heira

-0.66

POSITIVE LOGITS

 String

1.57

String

1.52

oporosis

0.85

 StringIO

0.83

setDo

0.78

trx

0.77

 Antara

0.77

WriteLiteral

0.77

StringCopy

0.76

 JLabel

0.76

Activations Density 0.062%

references to strings in code snippets or documentation

No Comments

No Known Activations