INDEX

Explanations

specific names and terms related to data structures and analysis in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 AssemblyCompany

-0.72

consulté

-0.67

moveToFirst

-0.65

voorbeeld

-0.64

endregion

-0.64

NAND

-0.64

-0.63

awe

-0.60

ntgen

-0.60

iedene

-0.59

POSITIVE LOGITS

pable

1.14

Jep

1.14

FAP

1.13

Bp

1.12

Jop

1.10

Jep

1.09

cip

1.09

bop

1.09

Bop

1.08

Cip

1.06

Activations Density 2.579%

specific names and terms related to data structures and analysis in scientific contexts

No Comments

No Known Activations