INDEX

Explanations

terms related to low measurements or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ThroughAttribute

-0.70

UnitTesting

-0.64

 NSCoder

-0.64

 gynhyrchwyd

-0.63

 StyleSheet

-0.63

StyleSheet

-0.63

GenerationType

-0.62

 gluta

-0.62

 engraçadas

-0.60

 longues

-0.59

POSITIVE LOGITS

LOW

1.00

Low

0.98

low

0.98

Low

0.88

 Lower

0.83

 Lowest

0.83

 lowest

0.82

Nied

0.82

 Lowry

0.81

 lows

0.81

Activations Density 0.274%

terms related to low measurements or conditions

No Comments

No Known Activations