INDEX

Explanations

references to errors in a technical context

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

SourceChecksum

-0.80

PerformLayout

-0.76

DockStyle

-0.69

setVerticalGroup

-0.67

esterday

-0.65

 Ressource

-0.64

 Monfieur

-0.61

droj

-0.57

GroupLayout

-0.56

 Savior

-0.56

POSITIVE LOGITS

0.66

 hoped

0.64

 HasFactory

0.64

<>();

0.60

Obrázky

0.59

redux

0.58

 happening

0.57

PyExc

0.57

.[

0.56

%">

0.55

Activations Density 0.191%

references to errors in a technical context

No Comments

No Known Activations