INDEX

Explanations

numeric values, particularly those in a coding or programming context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

CORBA

-0.61

geber

-0.58

')}}">

-0.57

 noexcept

-0.56

')}}

-0.54

 פרק

-0.54

 Neri

-0.54

Reentrant

-0.54

SystemColors

-0.53

Mox

-0.53

POSITIVE LOGITS

Value

2.37

 Value

1.24

VALUE

1.11

CurrentValue

0.89

 VALUE

0.86

getValue

0.85

setValue

0.84

HasValue

0.75

ThroughAttribute

0.73

addValue

0.70

Activations Density 0.111%

numeric values, particularly those in a coding or programming context

No Comments

No Known Activations