INDEX

Explanations

terms related to closed systems or structures

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

 AssemblyProduct

-1.04

QMetaType

-0.84

AppMethodBeat

-0.82

 CreateTagHelper

-0.80

ècie

-0.79

windigkeit

-0.78

styleable

-0.75

 HasFactory

-0.74

ParseTree

-0.74

AccessorTable

-0.73

POSITIVE LOGITS

 closed

2.23

 Closed

2.10

Closed

1.97

 closes

1.90

 closing

1.84

closed

1.84

 CLOSED

1.81

 clos

1.80

 closure

1.69

 Closing

1.68

Activations Density 0.071%

terms related to closed systems or structures

No Comments

No Known Activations