INDEX

Explanations

terms and phrases related to rates, performance, and data evaluation in organizational contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.69

no

-0.66

-0.63

-0.58

-0.56

-0.55

Se

-0.54

se

-0.54

POSITIVE LOGITS

 pleaſure

1.48

 purpoſe

1.46

 itſelf

1.36

 myſelf

1.35

 ſtate

1.34

 houſe

1.34

 themſelves

1.30

 Monfieur

1.27

 cauſe

1.24

 Jefus

1.24

Activations Density 0.343%

terms and phrases related to rates, performance, and data evaluation in organizational contexts

No Known Activations