INDEX

Explanations

specific geographical locations and sites

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

יקר

-0.43

protoimpl

-0.43

how

-0.41

odt

-0.41

AnchorTagHelper

-0.41

voire

-0.41

 servers

-0.41

jsk

-0.40

formen

-0.40

olk

-0.40

POSITIVE LOGITS

 surla

0.83

 ſever

0.76

 myſelf

0.76

sidemargin

0.75

ImageContext

0.74

Efq

0.74

Personendaten

0.73

tonode

0.73

 deſt

0.70

IntoConstraints

0.70

Activations Density 0.344%

specific geographical locations and sites

No Comments

No Known Activations