INDEX

Explanations

references to specific methods or procedures in a document

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

BeginInit

-0.82

InjectAttribute

-0.77

QMetaType

-0.68

 "..\..\..\

-0.65

Distribuzione

-0.65

IUrlHelper

-0.64

SharedCtor

-0.64

parsedMessage

-0.63

Rohy

-0.63

@"/

-0.63

POSITIVE LOGITS

 mentioned

0.98

 above

0.94

 described

0.87

 listed

0.87

mentioned

0.85

 below

0.84

above

0.82

 shown

0.79

 pictured

0.78

 outlined

0.77

Activations Density 0.705%

references to specific methods or procedures in a document

No Comments

No Known Activations