INDEX

Explanations

comparisons and equality checks in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

wahati

-0.67

 indietro

-0.66

dientemente

-0.65

 XNUMX

-0.64

 propOrder

-0.61

 biber

-0.60

 ExecuteAsync

-0.60

himovic

-0.59

InjectAttribute

-0.59

vénients

-0.59

POSITIVE LOGITS

==

0.82

interopRequire

0.75

===

0.68

ind

0.61

=='

0.60

==

0.58

 geslacht

0.57

ID

0.55

API

0.53

==(

0.53

Activations Density 0.180%

comparisons and equality checks in code

No Comments

No Known Activations