INDEX

Explanations

SQL-related terminology and database operations

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

 Majefty

-0.79

 Cæsar

-0.74

IonicModule

-0.74

 myſelf

-0.72

 leſs

-0.71

 calcetines

-0.69

 pleaſure

-0.69

 whoſe

-0.69

 Jefus

-0.69

 morire

-0.68

POSITIVE LOGITS

query

1.08

 query

0.72

Query

0.57

rawQuery

0.56

protoimpl

0.56

ny

0.56

 Query

0.55

CastException

0.55

“

0.54

 perfect

0.54

Activations Density 0.063%

SQL-related terminology and database operations

No Comments

No Known Activations