INDEX

Explanations

words related to specific locations or names

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

Mok

-0.91

Mok

-0.90

Moc

-0.79

Moc

-0.77

mok

-0.77

mok

-0.73

 Mocha

-0.71

-0.63

moc

-0.63

 mocha

-0.62

POSITIVE LOGITS

URLException

0.39

 mijne

0.39

✭✭

0.35

 '\\;'

0.33

 surla

0.33

pulseira

0.33

InvalidProtocol

0.33

wyg

0.32

VolleyError

0.32

rungsseite

0.32

Activations Density 0.011%

words related to specific locations or names

No Comments

No Known Activations