INDEX

Explanations

references to different character encodings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ScopeManager

-1.12

tagHelper

-0.98

 estekak

-0.97

 resourceCulture

-0.95

 صوتيه

-0.91

CodeAttribute

-0.89

 autorytatywna

-0.87

 ModelExpression

-0.84

 Winaray

-0.82

 NSCoder

-0.80

POSITIVE LOGITS

Diagnostics

1.80

 diagnostics

0.83

 Diagnostics

0.81

UTF

0.80

diagnostics

0.69

Diagnostic

0.55

LayoutPanel

0.55

 diagnostic

0.54

 diagnose

0.53

Diagnosis

0.52

Activations Density 0.016%

references to different character encodings

No Comments

No Known Activations