INDEX

Explanations

proper names and specific locations, particularly addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 snippetHide

-0.99

enumi

-0.96

 GoogleFonts

-0.95

WireFormat

-0.88

اریخ

-0.86

principalTable

-0.84

 ContentValues

-0.80

 للمعارف

-0.77

 GenerationType

-0.77

ritation

-0.77

POSITIVE LOGITS

 process

0.37

被

0.36

<eos>

0.36

om

0.34

can

0.34

0.33

стра

0.33

を手

0.33

st

0.33

os

0.33

Activations Density 0.273%

proper names and specific locations, particularly addresses

No Comments

No Known Activations