INDEX

Explanations

information related to user instructions and guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

igle

-0.40

AutoScaleMode

-0.39

 INSEE

-0.39

 ligiloj

-0.37

riment

-0.37

结

-0.37

 bootstra

-0.36

ství

-0.36

eqn

-0.36

Offered

-0.36

POSITIVE LOGITS

 requests

1.08

 request

0.99

requests

0.93

 Requests

0.93

 requesting

0.88

 requested

0.84

 demand

0.84

 demands

0.80

 REQUEST

0.80

Requests

0.80

Activations Density 0.330%

information related to user instructions and guidance

No Comments

No Known Activations