INDEX

Explanations

references to various types of letters and correspondence

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

Lähteet

-0.94

 Monfieur

-0.93

 ExecuteAsync

-0.88

 myſelf

-0.87

 propOrder

-0.86

ConstraintMaker

-0.85

 OFDb

-0.84

mylist

-0.83

Verweise

-0.82

 Roskov

-0.81

POSITIVE LOGITS

 letters

2.53

 letter

2.40

 Letters

2.26

 LETTER

2.20

letter

2.18

 Letter

2.15

Letter

2.10

Letters

2.10

 LETTERS

2.06

letters

2.04

Activations Density 0.042%

references to various types of letters and correspondence

No Comments

No Known Activations