INDEX

Explanations

references to programming libraries and frameworks, particularly in the context of code generation and APIs

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.99

enterOuterAlt

-0.87

AddTagHelper

-0.86

 AssemblyCulture

-0.86

 defaultstate

-0.86

 <=",

-0.80

localctx

-0.78

ioutil

-0.78

GOTREF

-0.75

 صوتيه

-0.75

POSITIVE LOGITS

<%

0.49

 mogelijk

0.43

dropIfExists

0.43

 Substrate

0.42

 Remember

0.42

morrow

0.42

cio

0.42

0.41

choly

0.41

Activations Density 0.453%

references to programming libraries and frameworks, particularly in the context of code generation and APIs

No Comments

No Known Activations