INDEX

Explanations

sections and references within a formal document or report

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

]--;

-0.64

 Theſe

-0.58

whom

-0.57

 himſelf

-0.56

 пищи

-0.53

vatten

-0.51

parken

-0.51

","+

-0.51

 damned

-0.49

 Unsplash

-0.49

POSITIVE LOGITS

 Sections

0.99

Sections

0.95

 sections

0.92

 SECTIONS

0.89

SECTION

0.87

 SECTION

0.85

 Section

0.82

#+#

0.81

SourceChecksum

0.80

 subsections

0.76

Activations Density 0.226%

sections and references within a formal document or report

No Comments

No Known Activations