INDEX

Explanations

references to fragments in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

PostMapping

-0.91

+#+#

-0.91

 Ishikawa

-0.83

 Kidman

-0.82

 upkeep

-0.82

leit

-0.80

@[

-0.80

contentLoaded

-0.79

 dowry

-0.79

 Melinda

-0.78

POSITIVE LOGITS

fragments

1.37

 fragment

1.36

Fragment

1.36

 Fragment

1.33

fragment

1.32

 fragments

1.30

 Fragments

1.29

Fragments

1.13

 FRAG

1.04

FRAGMENT

1.02

Activations Density 0.156%

references to fragments in a programming context

No Comments

No Known Activations