INDEX

Explanations

code related to output functions in programming languages

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

rungsseite

-0.72

parsedMessage

-0.62

formik

-0.60

tagHelperRunner

-0.59

Hentet

-0.58

Formik

-0.57

AddTagHelper

-0.54

Notae

-0.53

 '\\;'

-0.52

AccessorTable

-0.52

POSITIVE LOGITS

rø

0.36

SequentialGroup

0.36

 Kerja

0.35

 Púb

0.33

 InputDecoration

0.32

 öppna

0.31

 ouverts

0.31

 otwar

0.31

 referenties

0.31

inca

0.31

Activations Density 0.020%

code related to output functions in programming languages

No Comments

No Known Activations