INDEX

Explanations

database-related keywords and concepts, particularly around defining and using table schemas and keys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Henson

-0.49

 опро

-0.47

 nakalista

-0.47

DoubleQuotes

-0.47

UnknownFieldSet

-0.45

HttpConnection

-0.45

scored

-0.45

 despe

-0.44

 famí

-0.44

multirow

-0.43

POSITIVE LOGITS

 primary

1.17

 Primary

1.08

 PRIMARY

1.02

primary

1.00

PRIMARY

0.99

Primary

0.98

key

0.97

KEY

0.93

Key

0.92

Key

0.88

Activations Density 0.252%

database-related keywords and concepts, particularly around defining and using table schemas and keys

No Comments

No Known Activations