INDEX

Explanations

references to specific locations and spaces within a residential or architectural context

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

-0.59

-0.55

in

-0.52

an

-0.46

↵↵

-0.44

<eos>

-0.44

-0.43

 functional

-0.43

do

-0.42

-0.41

POSITIVE LOGITS

Efq

0.80

CWE

0.77

ViewFeatures

0.76

expandindo

0.76

 photolibrary

0.75

StoryboardSegue

0.74

Clik

0.71

posób

0.71

 myſelf

0.69

 lenker

0.68

Activations Density 0.063%

references to specific locations and spaces within a residential or architectural context

No Comments

No Known Activations