INDEX

Explanations

references to specific scientific or technical terms in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

AddTagHelper

-0.56

 faſt

-0.54

TagMode

-0.54

Tikang

-0.52

 Reſ

-0.50

 Photocase

-0.50

 Constitucional

-0.50

Ӕ

-0.49

 ſtand

-0.48

 pleaſure

-0.47

POSITIVE LOGITS

 consultato

0.52

OptionsMenu

0.51

 שוליים

0.43

 onOptions

0.42

 initComponents

0.40

 استنادى

0.40

IntoConstraints

0.39

ByVersion

0.39

 Ginger

0.38

ViewFeatures

0.38

Activations Density 0.000%

references to specific scientific or technical terms in a document

No Comments

No Known Activations