INDEX

Explanations

evaluative statements about characters or elements in a narrative

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

 MainAxisSize

-0.79

httphttps

-0.73

 ModelExpression

-0.70

Билгалдахарш

-0.68

 CreateTagHelper

-0.68

TemporalType

-0.65

setVerticalGroup

-0.64

 otomatig

-0.63

 nonUne

-0.63

yntaxException

-0.63

POSITIVE LOGITS

 chapters

0.93

 book

0.89

 readers

0.89

 reader

0.88

chapters

0.86

 author

0.84

 books

0.84

 characters

0.83

 Goodreads

0.77

characters

0.76

Activations Density 0.296%

evaluative statements about characters or elements in a narrative

No Comments

No Known Activations