INDEX

Explanations

references to errors and inconsistencies in data or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 civilised

-0.59

MemoryWarning

-0.59

AnchorStyles

-0.59

новништво

-0.59

 Bourgoin

-0.57

κτηρισ

-0.57

 <<<<<<<<<<<<<<

-0.56

ctable

-0.55

<bos>

-0.54

+};

-0.54

POSITIVE LOGITS

 unreliable

1.00

 poor

0.96

 poorly

0.93

 inefficient

0.89

 incomplete

0.89

 unstable

0.86

poor

0.79

 ineffective

0.79

 unsatisfactory

0.79

 inadequate

0.78

Activations Density 0.978%

references to errors and inconsistencies in data or information

No Comments

No Known Activations